# Vocuno Agent (Vai) Source: https://support.vocuno.com/agent/overview Vai is the Vocuno AI agent — chat in plain language to generate songs, edit audio, search the web, and run multi-step music workflows hands-free. Open the Agent ↗️ **Vai** is Vocuno's AI agent — a chat assistant that has access to every tool on the platform and can run full production workflows for you. Tell Vai what you want in plain English ("write a sad acoustic ballad and put my voice on it"), and it figures out the steps, calls the right tools, and shows you progress live. ## What Vai can do Vai has around 70 tools across every part of the platform: song generation (Suno, Udio, Mureka, MusicGPT, MiniMax, ElevenLabs, Lyria 3), stem separation, voice conversion, lyrics generation, audio capture from YouTube, audio edits, and search (web search, YouTube search, URL fetch). Replies stream live, with interactive cards for each generated song, stem, or voice conversion that update in real time. Multi-step requests work in one message: *"cover Wonderwall in a female voice"* makes Vai find the song, capture the audio, separate stems, and run the cover pipeline end-to-end while you watch the cards update. ## Inputs and credits You can type prompts or hold the mic button to dictate them. Agent messages are metered by the actual AI usage of your request — a typical message costs around 5 credits — and any tools the agent runs (song generation, stem split, etc.) deduct their normal credit cost. See [Credit Costs](/credit-costs) for the full list. ## Frequently asked questions Be specific about what you want — genre, mood, vocals, length. Vague prompts ("make me a song") still work, but precise ones produce better results faster. Yes — drop a file into the chat and Vai can run it through stem separation, voice conversion, de-reverb, or any other tool you ask for. Yes. Each conversation is auto-titled, saved, and you can rename, share via link, or delete it from the sidebar. Vai picks the most credit-efficient provider when possible. You can also tell it directly ("use Suno", "use a voice from Audimee") to control which model gets called. # Billing & Subscriptions Source: https://support.vocuno.com/billing-and-subscriptions Vocuno pricing, plan features, credit allocations, upgrades, downgrades, and how to manage your subscription. Vocuno is subscription-based — pick a plan and get a monthly credit allowance you can spend across every tool, AI engine, and distribution release. You can pay with Stripe (card) or PayPal, and manage your payment method, download invoices, or cancel anytime from your account settings. ## Plans | Plan | Monthly | Annual (per mo) | Monthly Credits | Extras | | ----------- | ------- | --------------- | --------------- | -------------------------------------------------------------------------- | | **Starter** | \$19 | \$18 | 1,500 | All AI engines, Studio DAW | | **Pro** | \$49 | \$34 | 10,000 | Everything in Starter, credit packs | | **Studio** | \$99 | \$69 | 30,000 | Unlimited creation mode, 10,000 bonus Marketplace credits, usage dashboard | Annual billing saves up to 30%. All plans include access to every AI engine — Suno, Udio, Mureka, MusicGPT, MiniMax, LALAL.ai, Audimee, ElevenLabs, Lyria 3 — plus the Studio DAW and the Vocuno Agent. ### The Studio plan The Studio plan is built for heavy creators. On top of 30,000 monthly credits it includes an opt-in **Unlimited** creation mode (fair-use throttled on the server), a separate **10,000-credit monthly allowance for the Marketplace**, and a dedicated usage dashboard in your account settings so you can track exactly where your credits go. ## Credits Credits are the universal currency for every action — generate a song, split stems, convert a voice, etc. Costs vary by tool and provider; see [Credit Costs](/credit-costs) for the full table. Credits reset on each billing cycle and don't roll over. ## Top-ups, upgrades & downgrades You can buy on-demand credit packs when you run out — packs range from 1,500 credits ($10) up to 214,000 credits ($1,000), with bonus credits on larger packs. Upgrades take effect immediately (extra credits added to your balance); downgrades apply at the next renewal. Cancellation keeps you on the plan until the end of the current cycle. ## Referrals & rewards Invite friends to Vocuno and you both earn bonus credits when they sign up. See the rewards page in your account for your personal referral link and current bonus amounts. ## Frequently asked questions Generations pause until the next renewal — your library and finished tracks stay accessible. You can buy a credit pack to keep going. No — credits for failed runs are auto-refunded. Yes. Every plan is available with identical pricing through both Stripe (card) and PayPal, on monthly or annual billing. Yes. Cancel from your account settings; access continues until the end of the current period. New accounts come with a small starter allowance so you can try the core tools before subscribing — including two free Vocuno covers and the always-free toolbox (BPM detector, chord finder, audio recognition, practice tools). Your library and finished tracks remain accessible — you keep everything you created. New generations require an active plan or remaining credits. Invoices are available in the Stripe customer portal, accessible from your Vocuno account settings. # Add Instrumental Source: https://support.vocuno.com/create/add-instrumental Upload a vocal recording and let Vocuno generate a matching instrumental backing — beats, harmony, and full production around your voice. Try it now! ↗️ **Add Instrumental** is the mirror of Add Vocals — you bring a vocal-only recording and Vocuno builds an instrumental around it. The pipeline generates instrumental covers with Suno that match your vocal's structure, isolates the backing track, and merges it under your original voice. ## Inputs Drop in your vocal-only file (or record directly in the browser) and optionally describe the **instrumental style** — for example "lo-fi beats", "orchestral strings", or "trap 140 bpm". Pick the **number of variations** you want (1, 2, 4, or 6 different instrumental takes). ## What you get Vocuno generates instrumental covers via Suno using your vocals as a structural reference, isolates the clean backing tracks, and mixes each one with your original vocal. The result is several finished mixes — same vocal, different instrumental treatments — ready to preview and download. ## Frequently asked questions Clean, dry vocal recordings work best. The cleaner the input, the better the AI can lock the instrumental to your phrasing. Yes — the optional style prompt influences the genre, mood, and instrumentation of the generated backing. Start with 2 to compare options without burning extra credits. Pick more if you want more A/B options. Suno picks up the tempo from your vocal phrasing and aligns the instrumental to it. # Add Vocals to a Track Source: https://support.vocuno.com/create/add-vocals-to-track Upload an instrumental or beat and let Vocuno write, sing, and layer AI vocals on top — choose the singer, gender, and lyrics. Try it now! ↗️ **Add Vocals** lets you bring an existing instrumental and have Vocuno layer AI vocals on top. Upload your beat, paste or auto-generate lyrics, pick a vocal gender, and Vocuno produces a finished mix with vocals sung over your track. ## Inputs Drop in any instrumental (MP3, WAV, FLAC, OGG, M4A). BPM is auto-detected, and you can paste **custom lyrics** or hit the sparkle button to write them with AI. Pick a **vocal gender** (Female / Male) and pick a quality mode. ## Fast vs Clean mode **Fast** runs Suno on your beat with an optional vocal style prompt and returns a couple of finished mixes — quickest path. **Clean** generates vocal covers, isolates the vocals, and shows you previews; you then pick the best take and the AI voice (Audimee or MusicGPT) before the final mix is rendered. ## Frequently asked questions MP3, WAV, FLAC, OGG, and M4A. Cleaner instrumentals (no vocal bleed) give better results. Yes — paste them in directly. Or use the sparkle button to call the [AI lyrics generator](/create/ai-lyrics-generator). Phase 1 generates and previews vocal takes. Phase 2 lets you pick which take and which AI singer to use before committing to the final voice conversion. Vocuno auto-detects BPM from the upload so the generated vocals lock to your tempo. # Lyrics Source: https://support.vocuno.com/create/ai-lyrics-generator Describe a theme, mood, or story and get complete song lyrics in seconds. Edit them, or send them straight to Create Song. Try it now! ↗️ Lyrics empty state The Lyrics tool writes full song lyrics — verses, chorus, bridge — from a short description. There are two tabs: **Generate** and **Refine**. ## Generate Type what the song is about in the **Describe your song** field and click **Generate Lyrics**. The draft appears on the right in a few seconds with sections already labeled. A good prompt usually has a mood, a genre, and a bit of story. For example: *"Upbeat summer road trip anthem, pop-rock, feeling free after a breakup."* Prompt filled in Once the lyrics are generated, every line is editable — click into it and change whatever you want. When you're happy with the draft, hit **Send to Create Song** to pass it straight into the [Create Song](/create/ai-song-generator) tool. ## Refine Switch to **Refine** when you already have lyrics and want to change something specific — the tone, a weak chorus, the rhyme scheme — without regenerating the whole song. Paste or keep your lyrics, describe what you want changed, and you'll get an updated version that leaves the rest alone. ## Frequently asked questions Yes — mention the genre, mood, or an era in your prompt (pop, hip-hop, 90s alt-rock, etc.) and the AI will match vocabulary, rhyme density, and structure. Yes. Every line is editable inline. For bigger rewrites, use Refine mode. Generate writes a new song from a prompt. Refine takes existing lyrics and improves a specific part without starting over. Yes. Use **Send to Create Song** and your lyrics prefill the Create Song tool, where you pick the music model and vocal settings. See the [Credit Costs](/credit-costs) page for the current cost per generation. # Create Song Source: https://support.vocuno.com/create/ai-song-generator Turn any text prompt or lyrics into a complete song with AI vocals and instrumentals. Powered by Suno, Udio, Mureka, MusicGPT, MiniMax, Lyria 3 and ElevenLabs Try it now! ↗️ Create Song form in Simple mode ## Simple Mode Enter your song description and select the music model your want and click on generate song. Your song preview should be ready in less than 30 seconds! \ If you wish your song to be instrumental only click on the option "Instrumental" ## Custom Mode In custom mode you will have way more options! \ \ You can add lyrics, select the gender of the vocal, say how much you want the model to be creative (weirdness parameter) and how much does the model has to follow your instructions (style influence parameter) Create Song form in Custom mode ## Cover Mode The Cover mode allows you to ask the model to follow closely an existing audio. \ \ Select your audio and then add the different parameter like in custom mode. Screenshot 2026 04 15 At 10 53 19 ## Models Available You can pick your generation engine from the provider dropdown: * **Suno** — V5.5 (default), V5, and V4.5 * **Vocuno** — the premium in-house pipeline, for when you want the highest quality output * **Udio** — high-fidelity generation, returns 2 tracks per call * **Mureka** — V9 (default), V8, V7.6, and O2; can generate up to 3 tracks or instrumentals per call * **MiniMax**, **MusicGPT**, **ElevenLabs** — alternative engines with their own sound * **Lyria 3** (Google) — full songs, or a fixed 30-second clip mode Not every provider is available in every mode: Custom mode supports Vocuno, Suno, Udio, Mureka, MiniMax, and Lyria 3, while Cover mode supports Suno, Vocuno, MusicGPT, MiniMax, and Mureka. See [Credit Costs](/credit-costs) for what each engine costs. Model selection dropdown ## Frequently asked questions You provide a text prompt describing the song you want — genre, mood, tempo — or paste your own lyrics. Vocuno sends your request to the AI engine you selected (Suno by default), which composes and produces the complete track: melody, arrangement, vocals, and mix. Most engines return two takes per generation so you can pick the better one. Yes. You can write lyrics from scratch, use the AI lyrics generator, or paste existing lyrics. The AI will compose the melody and arrangement around your words while matching the genre and mood you select. Vocuno supports all genres like pop, hip-hop, R\&B, rock, EDM, country, jazz, lo-fi, and many more. You can also describe hybrid styles or specific subgenres in your text prompt. A typical song takes a few minutes to fully render, but you'll usually hear a preview in under a minute.  Music generated with Vocuno can be used in your projects. Review the terms of service of the underlying AI providers (Suno, MusicGPT) for specific licensing details regarding commercial use. # De-noise & De-echo Source: https://support.vocuno.com/create/audio-cleanup Remove background noise, echo, and slapback from any recording with AI audio cleanup. Remove background noise ↗️ Remove echo ↗️ Vocuno's **Clean** suite fixes flawed recordings with a single upload: * **De-noise** — strips background noise, hiss, and hum * **De-echo** — removes echo and slapback reflections * **[De-reverb](/create/de-reverb)** — removes room reverb (its own page) All three share the same flow: upload a file (or pick one from your library), run it, and the cleaned MP3 appears in your library a few minutes later. Each cleanup run costs **20 credits**, and failed runs are refunded automatically. ## When to use which | Problem | Tool | | -------------------------------------- | --------- | | Constant hiss, hum, traffic, fan noise | De-noise | | Distinct repeats/slapback of the voice | De-echo | | "Recorded in a bathroom" roominess | De-reverb | Heavily damaged recordings sometimes need two passes — de-noise first, then de-reverb. ## Frequently asked questions Aggressive cleanup can dull a recording slightly. If the result sounds over-processed, try cleaning only the tool that matches your main problem rather than chaining all three. Yes — any audio works. For separating a voice from music entirely, use [Stems](/create/stems) instead. # Audio Mastering Source: https://support.vocuno.com/create/audio-mastering One-click AI mastering — polish loudness, clarity, and tonal balance, with optional reference-track matching. Try it now! ↗️ **Audio Mastering** polishes the loudness, clarity, and tonal balance of a finished track in one click — the final step before release. ## How to use it 1. Pick your source track (upload or from your library). 2. Optionally add a **reference track** — the master is matched toward its sound, so you can aim for the loudness and tone of a song you love. 3. Run it — **30 credits** per master, MP3 output. 4. Compare before/after with the built-in **A/B compare** player, then keep the winner. The mastered file lands in your library, ready for [Distribution](/distribute/overview). ## Frequently asked questions Last — after mixing in the [Studio](/using-the-studio) and exporting. Master the final stereo file, not individual stems. The AI analyzes the reference's loudness and tonal balance and pushes your master toward it. Pick a professionally released song in the same genre. # Audio Recognition Source: https://support.vocuno.com/create/audio-recognition Identify any song from an audio file — free, Shazam-style recognition with title, artist, and confidence score. Try it now — free ↗️ **Audio Recognition** identifies a song from an audio file, Shazam-style. Upload a clip (or pick something from your library) and get back the matched **title, artist, and a confidence score** — or "no match found" if the fingerprint doesn't hit. It's **completely free** — no credits, and it even works without an account on the public tool page (up to 30 MB per file). ## Good to know * Cleaner input → better matches. A clip with the main melody or vocals beats a noisy live recording. * Recognition finds *released* music. Your own AI generations won't match — that's expected. * Pairs well with [Capture Audio](/create/capture-audio): capture a track you heard somewhere, then identify it. ## Frequently asked questions A focused 15–30 second clip of the most recognizable part of the song works best — you don't need the whole track. How certain the fingerprint match is. High scores are near-certain; low scores are worth double-checking against the suggested title. # Audio to MIDI Source: https://support.vocuno.com/create/audio-to-midi Convert any audio recording into a MIDI file with detected notes, timing, and velocity — ready for your DAW or to drive other instruments. Try it now! ↗️ **Audio to MIDI** turns a recording into a MIDI file by detecting every note, its timing, and velocity. Hum a melody, drop in a vocal line, or upload an instrument loop — Vocuno extracts a clean MIDI you can drag into any DAW. ## How to use it Drop in audio (MP3, WAV, FLAC, AAC, OGG, Opus, AIFF) or record live in the browser. Vocuno runs **Spotify's Basic-Pitch** model directly in your browser — no upload needed, no server roundtrip — and returns a MIDI file plus an interactive piano roll preview. ## What you get The output is a standard `.mid` file with detected pitches, durations, and velocities, plus a count of total notes detected. Download it and drag straight into Logic, Ableton, FL Studio, or any DAW to drive a synth, sampler, or virtual instrument. ## Frequently asked questions Monophonic input (one note at a time) — humming, whistling, single-instrument lines. Polyphonic chords work but can produce noisier output. No — Basic-Pitch runs entirely in your browser, so the audio never gets uploaded to a server. Yes — preview it on the piano roll in Vocuno, then download and edit freely in your DAW. Audio to MIDI runs locally and doesn't consume Vocuno credits. # BPM Detector Source: https://support.vocuno.com/create/bpm-detector Detect the tempo of any audio file instantly — runs in your browser, no credits required. Try it now! ↗️ The **BPM Detector** analyzes an audio file and tells you its tempo — useful for matching beats, planning remixes, or syncing layers in the [Studio](/using-the-studio). Detection runs entirely in your browser, so the audio never leaves your device. ## How to use it Drop in an audio file (MP3, WAV, FLAC, OGG, M4A, AAC) or pick one from your library. The tool decodes the track locally with `web-audio-beat-detector` and returns a BPM value between 20 and 300. You can also override the detected value manually if you already know the tempo. ## Frequently asked questions No — BPM detection runs in your browser and doesn't consume any credits. No, only BPM. Key/scale detection isn't part of this tool. You can override the BPM with any value between 20 and 300 — useful for half-time / double-time songs where the algorithm picks the wrong multiple. Tracks with a clear, consistent beat. Free-tempo or rubato performances may not return a meaningful BPM. # Capture Audio Source: https://support.vocuno.com/create/capture-audio Pull audio straight from a YouTube or Instagram URL into your Vocuno library — ready for stem separation, voice conversion, or remixing. **Capture Audio** downloads audio from a YouTube or Instagram URL and stores it in your Vocuno library, ready to feed into any other tool. It's most often used through the [Vocuno Agent](https://vocuno.com/agent) — ask Vai to find a song and grab the audio, and the capture is built automatically. ## How it works Paste or hand the agent a YouTube or Instagram URL and Vocuno extracts the audio (up to 15 minutes) into an MP3, along with metadata like title, uploader, and duration. The capture appears as a live-updating card in chat and lands in your library when complete. ## What you can do with a capture Once captured, the audio is just like any uploaded file — you can run [Stem Separation](/create/stems), [Voice Conversion](/create/voice-conversion-1), [De-Reverb](/create/de-reverb), use it as a [Cover / Remix](/create/cover-remix) source, or feed it into the [Studio](/using-the-studio). Ask the agent to *"cover Wonderwall in a female voice"* and it captures, splits, and covers the song end-to-end. Each capture costs **10 credits**. Need volume? The **Batch Downloader** (included with annual plans) takes a whole list of links — YouTube, Instagram, SoundCloud, TikTok — and returns a ZIP of MP3s or WAVs. ## Frequently asked questions Captures are capped at 15 minutes per URL. YouTube and Instagram. Other sources can be uploaded as files. Into your library as audio files — you can rename, delete, or pass them into any other Vocuno tool. Captured material is subject to the source platform's terms and copyright law. Use it for personal exploration, sampling, or covers in line with those rules. # Chord Finder Source: https://support.vocuno.com/create/chord-finder Upload any recording and get a timed chord sheet with key detection — free. Try it now — free ↗️ **Chord Finder** analyzes guitar, piano, or any instrumental recording and returns a **timed chord sheet**: each chord with its timestamp and a confidence score, plus a detected key signature when the analysis is confident. Using the tool is **free**. You can upload a file, import from your library, or record directly with your microphone. Copying the chord sheet to your clipboard is free too; downloading it as a TXT file requires a paid plan. ## How to use it 1. Upload or record the audio you want analyzed. 2. Run the analysis — you'll get the chord timeline, chord/note counts, and the key. 3. Play along, copy the sheet, or (on a paid plan) download it as `songname-chords.txt`. ## Frequently asked questions Clear harmonic content — solo guitar, piano, or a full mix with prominent chords. Dense or heavily distorted mixes lower the confidence scores. Yes — pick any track from your library as the source and learn to play your own AI songs. # Cover Artwork Source: https://support.vocuno.com/create/cover-artwork Generate release-ready cover art from a prompt — five AI image models, 16 style presets, and automatic art direction from your song. Try it now! ↗️ **Cover Artwork** generates release-ready cover images from a text prompt. Point it at a song in your library and it will even art-direct itself — analyzing the track and auto-drafting a title, artwork prompt, and visual style to match the music. ## Providers | Provider | Model | Credits | Notes | | -------------------- | ----------- | ------- | --------------- | | Vocuno (recommended) | Premium | 200 | Highest quality | | OpenAI | GPT Image 2 | 120 | | | Seedream | v4.5 | 100 | | | Flux | 2 Max | 100 | | | MiniMax | Image-01 | 60 | Fastest | ## Options * **Song reference** — pick a library song to auto-generate the prompt and style from an AI analysis of the track * **16 style presets** — cinematic, album-cover, editorial, minimal, realistic, glitch, mixed-media, Y2K poster, grunge, noir, dream-pop, street, retro-film, luxury, surreal, or custom * **Aspect ratio** — 1:1 square, 4:5 portrait, 9:16 story, 16:9 wide * **Resolution** — 720p for fast drafts, 1080p for release-ready quality * **Seed** — set a number (0–1,000,000) to reproduce a result, or leave blank for a fresh one Results land in the **Cover Artwork** tab of your library, ready to attach to a release in [Distribution](/distribute/overview). ## Frequently asked questions Vocuno premium gives the strongest, most release-ready results. MiniMax is the fastest and cheapest for quick drafts — iterate there, then re-run your final prompt on Vocuno. Yes — reuse the same seed with a tweaked prompt to stay close to the original composition. # Cover / Remix Source: https://support.vocuno.com/create/cover-remix Re-sing and re-imagine any song with AI — upload a track, capture from YouTube or Instagram, and generate covers with slowed, reverb, or nightcore effect mixes. Make a cover ↗️ Cover / Remix page **Cover / Remix** takes an existing song and regenerates it in a new style — new voice, new genre, new energy — while following the original closely. It's the tool behind every "AI cover" on Vocuno. ## Sources Your reference track can come from anywhere: * **Upload** — MP3, WAV, FLAC, OGG, or M4A * **YouTube or Instagram** — paste a link (or search, e.g. *"Adele Hello"*) and Vocuno captures the audio for you * **Your library** — any song or stem you've already created or captured ## How it works 1. Drop in your source song (or pick one of the suggested popular tracks). 2. Choose **With Vocals** or **Instrumental**, and optionally write new lyrics. 3. Describe the target style ("electro, rock emo, drums…") and add style tags. 4. Pick your **effect mix** — each generation produces **3 variations**, split between: * **Normal** — straight cover, with an optional manual BPM shift * **Slowed + reverb** * **Speed up / nightcore** 5. Generate. Covers land in your library and can be published to the [Listen covers feed](/listen/overview). ## Providers The full-screen `/cover` page runs on the **Vocuno** engine, which is built for covering songs — including copyrighted ones for personal use. Cover mode inside [Create Song](/create/ai-song-generator) also supports Suno, MusicGPT, MiniMax, and Mureka; note that **Suno covers only work with original songs you own the rights to** — for copyrighted material, use Vocuno Cover. ## Free covers Every new account gets **2 free Vocuno covers** (a one-time allowance — failed runs don't count against it). After that, covers use your plan's credits, and [Studio plan](/billing-and-subscriptions) members get a daily included Vocuno-cover allowance on top. ## Frequently asked questions With the Vocuno engine, yes — for personal listening and sharing within the Vocuno community. Distribution of covers to streaming platforms has additional licensing requirements; see [Copyright & Licensing](/faq/copyright-and-licensing). Each cover run produces 3 variations so you can pick the take that fits best. The effect-mix counters control how many of each style (normal, slowed + reverb, nightcore) you get. Yes — write your own lyrics in the lyrics panel, or leave it empty and toggle Instrumental for a vocal-free version. # Create Vocals Source: https://support.vocuno.com/create/create-vocals Generate a full song with AI vocals — pick any singer, any gender, any style — from a text prompt and lyrics. Try it now! ↗️ The **Create Vocals** pipeline writes, sings, and mixes a complete song for you. Describe the song, optionally bring your own lyrics, choose a vocal gender, and the pipeline generates the track with Suno, isolates the vocals, and converts them onto the AI singer of your choice. ## Inputs Fill in a **song description** (mood, genre, tempo) and optionally paste **lyrics** — or hit the sparkle button to draft them with AI. Pick a **vocal gender** (Female / Male) and a **quality mode**. ## Fast vs Clean mode **Fast** generates and previews a finished track in one go using Suno's native vocals — quickest path to a result. **Clean** runs the full pipeline: Suno generates the song, vocals are isolated, and you then pick an AI singer from the **Audimee** or **MusicGPT** voice catalog (100+ voices, previews included) to re-sing your track. The result is a polished mix with the voice you chose. ## Frequently asked questions Yes. Paste them in or generate them with the sparkle button, which calls the [AI lyrics generator](/create/ai-lyrics-generator) inline. Fast keeps Suno's original vocals. Clean isolates them and lets you pick a different AI singer to re-sing the track. Yes — every voice in the picker has a preview clip. Star your favorites to keep them at the top. Fast mode finishes in a couple of minutes. Clean mode takes 3–5 minutes end-to-end. # De-Reverb Source: https://support.vocuno.com/create/de-reverb Strip room reverb and echo from a vocal recording with one click — clean, dry vocals ready for production. Try it now! ↗️ **De-Reverb** removes room reverb, echo, and ambience from a vocal recording so the result sounds dry and studio-ready. Drop in a wet vocal, and Vocuno returns a cleaned-up version alongside your original for A/B comparison. ## How to use it Drop in any vocal file (MP3, WAV, FLAC, AAC, OGG, Opus, AIFF) or import one from your library. Vocuno runs it through the reverb-removal model and shows a live progress bar. When it's done, you get two tracks: the dry vocal and the original. Sibling tools [De-noise & De-echo](/create/audio-cleanup) handle background noise and echo the same way. ## When to use it Run de-reverb before [Voice Conversion](/create/voice-conversion-1) or [Transform Vocals](/create/transform-vocals) when your input was recorded in a reverberant space — bathroom, hallway, untreated room. Drier inputs give cleaner conversions and better stem isolation downstream. ## Frequently asked questions MP3, WAV, FLAC, AAC, OGG, Opus, and AIFF. De-reverb is tuned for vocals. For mixed audio, run [Stem Separation](/create/stems) first to extract the vocal, then de-reverb. Each cleanup run costs 20 credits, and failed runs are refunded automatically. See [Credit Costs](/credit-costs). Light to moderate reverb cleans up well. Extreme cases (long tails, deep cathedral spaces) may leave residual ambience. # Extend Song Source: https://support.vocuno.com/create/extend-song Make any track longer with AI — extend a song's ending, add new sections, and keep the style consistent. Try it now! ↗️ **Extend Song** takes an existing track — one you generated on Vocuno or one you upload — and continues it with AI, keeping the style, tempo, and feel consistent. Use it to turn a short generation into a full-length song, add an outro, or keep a great idea going. ## Providers | Provider | Credits | | -------------- | ------- | | Suno (default) | 75 | | MusicGPT | 60 | | Mureka | 100 | See [Credit Costs](/credit-costs) for the full pricing table. ## How to use it 1. Open the Extend Song tool from the creation menu. 2. Pick the track to extend from your library, or upload one. 3. Choose the provider and describe how the extension should continue (optional). 4. Generate — the extended track appears in your library. ## Frequently asked questions Yes — the AI listens to your source track and continues in the same style, tempo, and key. A short direction prompt helps steer new sections. Yes, you can chain extensions to keep growing a track. Each extension is a separate generation. # File Converter Source: https://support.vocuno.com/create/file-converter Convert audio between MP3, WAV, FLAC, AIFF, OGG, Opus, and AAC — fast, free, and lossless when you need it. Try it now! ↗️ The **File Converter** turns one audio format into another — handy when a streaming platform expects WAV, your DAW prefers FLAC, or you need a smaller MP3 for sharing. Conversion runs server-side and is free, with no credit cost. ## Supported formats | Type | Formats | | ------------ | ---------------------------------- | | **Lossless** | WAV, FLAC, AIFF | | **Lossy** | MP3, OGG (Vorbis), Opus, AAC / M4A | ## How to use it Drop in any audio file (or import from your library). The converter detects the source format and pre-selects a sensible output; pick a different one from the dropdown if needed. Conversion starts as soon as you choose the output format, and the result downloads to your browser. ## Frequently asked questions No — file conversion is free and unlimited. Lossless → lossless (e.g., WAV → FLAC) preserves quality. Going from a lossy format to anything else will not recover lost detail. For mastering, stick to WAV or FLAC. Common tags are preserved when the target format supports them. Cover art may be re-embedded in MP3, FLAC, and AAC outputs. Reasonable file sizes work fine. Very large files (over an hour of lossless audio) may take longer to convert. # Mashup Source: https://support.vocuno.com/create/mashup Blend two tracks into one AI-generated mashup on Vocuno. Try it now! ↗️ The **Mashup** tool blends two source tracks into a single new song. Pick two tracks — from your Vocuno library or uploaded files — and the AI combines them into one cohesive mashup, matching the energy of both sources. ## How to use it 1. Open the Mashup tool from the creation menu. 2. Select your two source tracks (library items or uploads — most common audio formats work, including WAV; Vocuno converts them automatically). 3. Optionally describe the direction you want the mashup to take. 4. Generate — the result lands in your library like any other creation. A mashup costs **50 credits** per generation — see [Credit Costs](/credit-costs). ## Frequently asked questions MP3 works out of the box, and other common formats like WAV are automatically converted before generation — you don't need to convert anything yourself. Yes — anything in your library (generated songs, stems, captures) can be a mashup source, alongside direct uploads. Mashups are generative, so each run is different. Try again with a more specific direction prompt, or use different source sections. # Mixing & the Mixing Agent Source: https://support.vocuno.com/create/mixing One-click mixing presets and an AI mixing chat — describe how you want your track to sound and the agent makes it happen. Try it now! ↗️ Vocuno gives you two ways to mix a track without touching an EQ: curated one-click **presets**, and a conversational **Mixing Agent**. ## Mixing presets — 8 credits Twelve curated presets, applied instantly to any track: * **EQ**: Bass Boost, Bass Reduction, Treble Boost, Warm Vintage, Vocal Clarity * **Creative**: Underwater, Telephone, FM Radio, Vinyl Lo-fi * **Spatial**: Cathedral Reverb, Slapback Echo * **Utility**: Loudness Boost Each preset application costs **8 credits** and returns a new processed file. ## The Mixing Agent The Mixing Agent is a chat: pick a track, then describe what you want — *"make it warmer"*, *"more space on the vocals"*, *"give it a vinyl feel but keep the low end tight"*. The agent applies the processing and returns new audio; edits chain across the conversation, so you can keep refining ("a bit less reverb now") until it's right. It's also available inside the [Studio](/using-the-studio) dock. Messages are metered by actual AI usage — roughly **25 credits per message** for a typical request, and you need a balance of at least 10 credits to start a turn. ## Frequently asked questions Presets for quick, predictable results at low cost. The agent when you can hear what's wrong but want to describe the fix in plain language. Every step returns a new file — your original is untouched, and earlier versions stay in the run history. # Toolbox Overview Source: https://support.vocuno.com/create/more-tools Every Vocuno tool at a glance — creation, vocals, processing, cleanup, analysis, and free practice utilities. Everything in the Vocuno toolbox, grouped the way it appears in the creation menu at [vocuno.com/app](https://vocuno.com/app). Tools marked **free** never cost credits. ## Song creation [Create Song](/create/ai-song-generator) · [Cover / Remix](/create/cover-remix) · [Extend Song](/create/extend-song) · [Mashup](/create/mashup) · [Cover Artwork](/create/cover-artwork) ## Vocals & voice [Create Vocals](/create/create-vocals) · [Add Vocals](/create/add-vocals-to-track) · [Add Instrumental](/create/add-instrumental) · [Transform Vocals](/create/transform-vocals) · [Voice Conversion](/create/voice-conversion-1) · [Voice Cloning](/create/voice-cloning) · [Text to Speech](/create/text-to-speech) ## Processing [Stems](/create/stems) · [Sound Generator](/create/sound-generator) · [Audio Mastering](/create/audio-mastering) · [Mixing & Mixing Agent](/create/mixing) ## Cleanup [De-reverb](/create/de-reverb) · [De-noise & De-echo](/create/audio-cleanup) · [File Converter](/create/file-converter) *(free)* ## Analysis [Capture Audio](/create/capture-audio) · [Song Analysis](/create/song-analysis) · [Audio Recognition](/create/audio-recognition) *(free)* · [Chord Finder](/create/chord-finder) *(free)* · [BPM Detector](/create/bpm-detector) *(free)* · [Audio to MIDI](/create/audio-to-midi) *(free)* ## Writing [AI Lyrics Generator](/create/ai-lyrics-generator) · [Writing Tools — Style Booster & Creation Prompts](/create/writing-tools) · [Persona Builder](/create/persona-generator) ## Advanced Studio tools [Replace Section, Timestamped Lyrics, Stem-to-MIDI, Music Video](/create/studio-tools) ## Practice suite (free) [Online Tuner, Pitch Detector, Vocal Range Finder, Metronome, Tap BPM, and calculators](/create/practice-tools) ## Power features * **Batch Downloader** — paste many links (YouTube, Instagram, SoundCloud, TikTok) and get a ZIP of MP3s or WAVs. Included with annual plans. # Persona Builder Source: https://support.vocuno.com/create/persona-generator Turn a generated track into a reusable style or voice persona, and carry that identity into every new song you create. Try it now! ↗️ The **Persona Builder** captures what makes one of your generated tracks special — its voice or its style — and turns it into a reusable **persona**. Apply the persona to future generations and every new song carries the same artist identity, which is how you build a consistent sound across a whole catalogue. ## How to use it 1. Pick a Suno-generated song from your library (use the song's menu to send it to the Persona Builder). 2. Name the persona, give it a style label and a description. 3. Optionally select the exact segment (start/end seconds) that best captures the voice. 4. Create — costs **50 credits**. ## Using a persona In [Create Song](/create/ai-song-generator), select your persona and choose whether to apply it as a **style persona** (the sonic character) or **voice persona** (the singer). Combine it with your own lyrics for a consistent artist project, album, or series. ## Frequently asked questions A [cloned voice](/create/voice-cloning) reproduces a real voice from a recording you own. A persona captures the identity of a track you generated — voice or overall style — without needing any real-world recording. No — personas are built from tracks generated on Vocuno (Suno engine). For external audio, look at [Voice Cloning](/create/voice-cloning) or [Cover / Remix](/create/cover-remix). # Practice Tools Source: https://support.vocuno.com/create/practice-tools Seven free musician utilities — tuner, pitch detector, vocal range finder, metronome, tap BPM, and delay/frequency calculators. No account needed. Vocuno ships a suite of **seven free practice utilities**. They run entirely in your browser — audio never leaves your device, there's no credit cost, and no account is needed. ## The tools * **[Online Tuner](https://vocuno.com/app?tool=online-tuner)** — real-time tuner for guitar, bass, violin, ukulele, or voice, with cents-sharp/flat readout and instrument presets (including drop D and chromatic). * **[Pitch Detector](https://vocuno.com/app?tool=pitch-detector)** — live note detection with note name, octave, frequency, cents deviation, and a pitch-history trace of your singing or playing. * **[Vocal Range Finder](https://vocuno.com/app?tool=vocal-range-finder)** — guided test that captures your lowest and highest comfortable notes and estimates your voice type, from bass to soprano. * **[Metronome](https://vocuno.com/app?tool=metronome)** — precise click with BPM control, time signatures, subdivisions (quarters to sixteenths and triplets), accented downbeats, and built-in tap tempo. * **[Tap BPM](https://vocuno.com/app?tool=tap-bpm)** — tap along to any song to find its tempo; rolling average with outlier filtering and a confidence score. No microphone needed. * **[BPM Delay Calculator](https://vocuno.com/app?tool=bpm-delay-calculator)** — convert BPM into delay times in milliseconds for every note value (including dotted and triplet) — for tempo-synced delays, echoes, and reverb pre-delay. * **[Note Frequency Calculator](https://vocuno.com/app?tool=note-frequency-calculator)** — convert any note to Hz with an adjustable A4 reference (default 440), with a full octave table for synthesis, tuning, and EQ work. ## Frequently asked questions Yes — all seven are free with no credit cost and no account required. Processing happens locally in your browser. The tuner, pitch detector, and vocal range finder listen through your mic to analyze pitch — the audio is processed on your device and never uploaded. # Song Analysis Source: https://support.vocuno.com/create/song-analysis Get an AI breakdown of any original song — genre, mood, instrumentation, and a reusable style prompt for your next generation. Try it now! ↗️ **Song Analysis** listens to an original song and produces a structured breakdown: genre, mood, instrumentation, lyric structure, and — most usefully — a **reusable style prompt** you can paste straight into [Create Song](/create/ai-song-generator) to generate new music in the same direction. ## Providers | Provider | Credits | What you get | | -------------------- | ------- | ------------------------------------------------------------------------------------------------------- | | **Vocuno** (default) | 10 | Original-song style analysis: genre, mood, instrumentation, lyrics, production direction | | **Mureka** | 100 | Combines Mureka's Describe + Recognize models for deeper musical direction and lyric-structure analysis | ## How to use it 1. Upload a song you own, or pick one from your library. (The tool is for original songs — don't upload copyrighted material.) 2. Pick a provider and run. 3. Open the result in the sidebar: copy the style prompt into a new generation, or study the lyric-structure breakdown. ## Frequently asked questions Treat it as a starting point: paste it into Create Song's description, then push it somewhere new ("…but darker, half-time drums"). It captures the recipe; you change the flavor. Start with Vocuno (10 credits). Reach for Mureka when you need a deeper read on musical direction and structure and the 100 credits are worth it. # Sound Generator Source: https://support.vocuno.com/create/sound-generator Generate loops, textures, risers, ambience, and sound effects from a text prompt — seven AI engines with loop mode, tempo, and key control. Try it now! ↗️ The **Sound Generator** creates loops, textures, impacts, risers, ambience, and short audio beds from a text description — the building blocks for your productions, without digging through sample libraries. ## Providers | Provider | Best for | Duration | Credits | | --------------------- | ----------------------------------------------------------------- | -------- | -------- | | **Suno V5** (default) | Musical sound loops with seamless loop mode, BPM and key control | — | 30 | | **ElevenLabs SFX** | Cinematic sound effects and foley | 0.5–30s | 60 | | **MusicGPT Sound** | Prompt-based audio textures | 5–60s | 40 | | **Kling SFX** | Short cinematic effects | 3–10s | 60 | | **ACE-Step** | Longer prompt-to-music beds, instrumental mode, reproducible seed | 5–240s | 60 | | **MiniMax Music 2.6** | Structured music beds with lyrics or structure tags | — | 60 | | **Mureka BGM** | Background music (V9/V8/V7.6), up to 3 variations, MP3/WAV/FLAC | — | 75/track | ## Common controls Every provider takes a text prompt; depending on the engine you can also set **loop mode**, **tempo**, **key**, **duration**, and a **seed** for reproducible results. Generated sounds land in the **Sounds** tab of your library — ready to drag into the [Studio](/using-the-studio) or layer into a mashup. ## Frequently asked questions Suno V5 for musical loops (it's also the cheapest), ElevenLabs for realistic sound effects, ACE-Step when you need a longer instrumental bed. Suno's loop mode and ElevenLabs' loop option are built for seamless looping. For other providers, trim the tail in the Studio for a clean loop point. # Stems Source: https://support.vocuno.com/create/stems Split any song into vocals, instrumentals, drums, bass, and more — eight stem-separation engines in one tool. Click here to try! ↗️ **Stems** extracts the individual components of a track. Have a song with vocals and want just the instrumental? An a cappella of the vocal? The isolated bassline? This tool pulls out exactly the stem you need. Upload your audio (MP3, WAV, FLAC, OGG, M4A) or pick a track from your library. By default the tool splits **vocals + instrumental**. ## Custom stems Switch to custom mode to extract specific parts: * Drums, Bass * Guitar (acoustic or electric) * Piano / Keys * Strings, Woodwinds * Backing Vocals ## Models available You can choose between several separation engines — each with its own character: * **Vocuno** — the in-house advanced splitter (30 credits, or 60 for the full multi-stem set) * **LALAL.ai** — best general-purpose option with the widest custom-stem support (20 credits/minute) * **Moises**, **BandLab Splitter**, **LANDR Stems** — alternative engines worth trying when a mix is stubborn * **MusicGPT** (20 credits) and **Mureka** (50 credits) — quick vocal/instrumental splits * **Suno** — only for tracks generated with a Suno model inside Vocuno (30 credits, 60 for advanced) See [Credit Costs](/credit-costs) for the full pricing table. ## Frequently asked questions Start with Vocuno or LALAL.ai. If a particular mix separates poorly, try another engine — results genuinely differ per song. Everything — remix them in the [Studio](/using-the-studio), run the vocal through [Voice Conversion](/create/voice-conversion-1), convert a melody with [Stem-to-MIDI](/create/studio-tools), or build a [Mashup](/create/mashup). The tool works on any audio, but what you do with the output matters — see [Copyright & Licensing](/faq/copyright-and-licensing). # Advanced Studio Tools Source: https://support.vocuno.com/create/studio-tools Power tools for finished tracks — replace a section, get word-synced lyrics, convert stems to MIDI, and generate a music video. These tools operate on tracks you've already generated — refining, extending, and repackaging finished work. They're available from the creation menu and inside the [Studio](/using-the-studio) AI dock. ## Replace Section — 50 credits Regenerate just one part of a song without rebuilding the whole track. Pick the source track, select a start/end time range, describe what should happen in that section (optionally with full lyrics, style tags, and vocal gender), and the AI infills only that range. Providers: Suno (50 credits) or MusicGPT (60 credits). The result is a new edited track — your original stays untouched. Use it to fix a weak bridge, rewrite one verse, or swap a chorus while keeping everything you already love. ## Timestamped Lyrics — 10 credits Get **word-by-word synced lyrics** for any of your generated tracks. Perfect for lyric videos, karaoke-style displays, or checking exactly where each line lands. ## Stem-to-MIDI — 20 credits Convert a finished [stem separation](/create/stems) into MIDI notes — take the bassline or melody of a track into your DAW as editable notes. (For converting a raw audio file directly, the free [Audio to MIDI](/create/audio-to-midi) tool does that without a stem split.) ## Music Video — 30 credits Generate an **MP4 visualizer video** for a finished track — a ready-to-post video for YouTube, TikTok, or Instagram without opening a video editor. ## Frequently asked questions They work on the generation itself (its stems, lyrics timing, and structure), which is only available for tracks created on Vocuno — not arbitrary uploads. Yes — a common flow: Replace Section to fix the bridge → Timestamped Lyrics for the lyric video → Music Video for the visual → master and release. # Text to Speech Source: https://support.vocuno.com/create/text-to-speech Turn any script into natural speech with ElevenLabs voices — voiceovers, narration, and spoken intros, straight to MP3. Try it now! ↗️ **Text to Speech** turns a script into natural spoken audio using ElevenLabs voices — for voiceovers, narration, spoken-word intros, or podcast segments. Output is MP3 (44.1 kHz, 128 kbps). ## How to use it 1. Paste or write your script — up to **5,000 characters** per run (a live counter keeps you honest). 2. Browse the voice library and preview voices until one fits. 3. Pick a model: **Multilingual v2** (default, best quality), **Turbo v2.5**, or **Flash v2.5** (fastest). 4. Optionally fine-tune the voice settings: stability, similarity, style, speed (0.7×–1.2×), and speaker boost. 5. Generate — the result lands in the **Speech** tab of your library. Pricing is **80 credits per started 1,000 characters** — a 2,500-character script costs 240 credits. ## Frequently asked questions Yes — clone it first with [Voice Cloning](/create/voice-cloning) (ElevenLabs IVC) and it appears in your voice list. The default Multilingual v2 model speaks dozens of languages — write your script in the target language and pick a voice that suits it. Yes — anything in your Speech library tab can be pulled into the [Studio](/using-the-studio) as a track, or layered into any pipeline that accepts library audio. # Transform Vocals Source: https://support.vocuno.com/create/transform-vocals Re-sing a vocal performance with a different AI voice while keeping the original lyrics — auto-transcribed, then re-generated and mixed. Try it now! ↗️ **Transform Vocals** takes a vocal performance and re-sings it with a different voice. Vocuno transcribes the lyrics from your audio, generates fresh vocal takes with Suno that follow the same words, then optionally converts them onto an AI singer of your choice. ## How it works Upload a vocal-only file (or record one in the browser), and Vocuno auto-transcribes the lyrics — you can edit the transcription before generation. Pick a **vocal gender** and **quality mode** (Fast or Clean), then run. In **Clean** mode, the pipeline pauses after generating Suno takes and isolating the stems. You then pick the best take and an AI voice (Audimee or MusicGPT), and Vocuno renders the final converted mix. ## Frequently asked questions No — Vocuno auto-transcribes them from your upload. You can edit any line before generation. [Voice Conversion](/create/voice-conversion-1) directly swaps the voice on your existing audio. Transform Vocals re-sings the song from scratch using your lyrics, which often sounds more natural for full performances. Yes — flip the Female / Male toggle to influence the new vocal character. Clean, dry vocal recordings with no instrumental bleed give the best transcription and generation quality. # Voice Cloning Source: https://support.vocuno.com/create/voice-cloning Clone a singing or speaking voice from a sample and reuse it in your Vocuno songs — powered by Suno, ElevenLabs, and Mureka. Try it now! ↗️ **Voice Cloning** creates a reusable voice from an audio sample — sing a hook once and generate whole songs in that voice afterwards. Voice cloning requires a paid plan (Pro, Studio, or annual Starter). ## Providers | Provider | Type | Credits | How it works | | ---------------------- | ------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Suno Voice** | Singing | 100 | Upload a vocal sample and select a clean segment (about 10 seconds). Suno gives you a verification phrase to record back — this proves the voice is yours — then creates the clone. You can set the language, singer skill level, and a singing-style description. | | **ElevenLabs IVC** | Speech | 120 | Instant clone from one or more clean recordings, with optional background-noise removal and voice metadata (language, accent, gender, age). | | **Mureka Vocal Clone** | Singing (pro) | 3,750 | A studio-grade reusable vocal identity from a clean solo-vocal sample. Saved-clone slots are limited: 1 on Pro, 3 on Studio. | Your sample can be uploaded, recorded in the browser, or imported from your library. ## Using a cloned voice Saved voices live in the Voice Cloning tool. For singing clones (Suno and Mureka) hit **"Use voice in a song"** — it opens [Create Song](/create/ai-song-generator) with your voice preselected, and every generation sings in your cloned voice. ElevenLabs speech clones are available in [Text to Speech](/create/text-to-speech). ## Frequently asked questions It's a safety measure: reading the phrase back proves you control the voice being cloned, preventing cloning someone else's voice from a recording. A clean, dry solo voice — no music, no reverb, no background noise. If your sample has instruments, run it through [Stems](/create/stems) first to isolate the vocal. It builds a full professional vocal identity on Mureka's infrastructure, which has a much higher underlying cost. Use Suno Voice for everyday cloning. # Voice Conversion Source: https://support.vocuno.com/create/voice-conversion-1 Convert any vocal recording into a different AI voice with one click — pick from 100+ singers, adjust pitch, keep the original phrasing. Try it now! ↗️ **Voice Conversion** swaps the voice on an existing vocal recording without re-singing it. Upload your audio, pick an AI singer, and the original phrasing, timing, and emotion are preserved — only the timbre changes. ## How to use it Drop in a vocal file (MP3, WAV, FLAC, AAC, OGG, M4A) or import one from your library. Pick a **provider** (Audimee or MusicGPT), filter by **gender**, and tap any voice in the grid to preview it. Adjust the **pitch shift** (-12 to +12 semitones) if you want to move the key, then hit **Convert Voice**. ## Voice catalog Both **Audimee** and **MusicGPT** offer 50+ male and female voices each, with preview clips you can play before committing. Star your favorites to keep them at the top of the grid for next time. ## Frequently asked questions Voice Conversion directly swaps the voice on your audio in one shot. [Transform Vocals](/create/transform-vocals) re-generates the performance from scratch using Suno — better for full takes that need a more natural feel. Dry, isolated vocals (no instrumental bleed). If your file is mixed, run it through [Stem Separation](/create/stems) first. When the source vocal sits in a key that doesn't suit the target voice — e.g., a low male take going to a higher female voice usually benefits from +5 to +12 semitones. Voice Conversion is billed per minute of input audio. See [Credit Costs](/credit-costs) for the exact rate. # Writing Tools Source: https://support.vocuno.com/create/writing-tools Style Booster expands rough style ideas into production-ready prompts; Creation Prompts is your personal prompt history across every tool. Two small tools that make every other tool better: one improves your prompts, the other remembers them. ## Style Booster Try it now! ↗️ **Style Booster** expands a rough style idea into a production-ready style prompt. Type *"sad indie folk"* and get back a detailed description covering instrumentation, mood, tempo feel, and production character — the kind of prompt that gets consistently better generations. It costs **10 credits** per boost, and it's also embedded directly next to style fields across the platform (Create Song, Mashup, and more) so you can boost in place without switching tools. ## Creation Prompts Browse your prompts ↗️ **Creation Prompts** is your personal prompt history — every prompt you've used across Song, Create Vocal, Add Vocals, Transform Vocals, and Lyrics, grouped by tool. For each prompt you can: * **Replay the result** when the audio is still in your library * **Reuse it** — one click re-opens the original tool with the prompt pre-filled It's free and great for iterating: find the prompt behind your best track, tweak one word, and run it again. ## Frequently asked questions No — it returns improved prompt text, written back into the style field. The audio generation (and its normal credit cost) happens when you then generate. Yes — Creation Prompts only shows your own history, visible only to you. # Credit Costs Source: https://support.vocuno.com/credit-costs How many credits each action costs on Vocuno. Every action on Vocuno uses credits from your monthly plan. The tables below list the cost of each action. Some actions have different costs depending on which model or provider you pick. Your plan includes a set number of credits each month. Unused credits do not roll over unless stated otherwise on your plan. ## Song Creation | Action | Provider / Model | Credits | Unit | Output | | -------------------- | ---------------- | ------- | ---------- | --------------------------- | | Generate Song | Suno (default) | 50 | per call | 2 songs | | Generate Song | Vocuno (premium) | 250 | per call | 1 song | | Generate Song | MusicGPT | 50 | per call | 2 songs | | Generate Song | Udio | 75 | per call | 2 tracks | | Generate Song | Mureka | 75 | per track | 1–3 tracks (75 / 150 / 225) | | Generate Song | MiniMax | 100 | per call | 1 song | | Generate Song | Lyria 3 | 100 | per call | 1 song | | Generate Song | ElevenLabs | 200 | per minute | 1 song | | Extend Song | Suno | 75 | per call | 1 extension | | Extend Song | MusicGPT | 60 | per call | 1 extension | | Extend Song | Mureka | 100 | per call | 1 extension | | Upload & Cover Audio | Suno | 50 | per call | 1 cover | | Mashup | Suno | 50 | per call | 1 mashup | | Replace Section | Suno | 50 | per call | 1 edit | | Replace Section | MusicGPT | 60 | per call | 1 edit | | Generate Persona | Suno | 50 | per call | 1 persona | | Music Video | Suno | 30 | per call | 1 video | ## Cover Art | Action | Provider | Credits | Unit | | ------------------ | ---------------- | ------- | -------- | | Generate Cover Art | Default | 50 | per call | | Generate Cover Art | MiniMax Image | 60 | per call | | Generate Cover Art | Seedream | 100 | per call | | Generate Cover Art | Flux | 100 | per call | | Generate Cover Art | OpenAI | 120 | per call | | Generate Cover Art | Vocuno (premium) | 200 | per call | ## Vocals & Voice | Action | Provider | Credits | Unit | Output | | ------------------ | ---------- | ------- | -------------------- | --------------- | | Add Vocals | Suno | 50 | per call | 1 vocal track | | Add Vocals | MusicGPT | 60 | per call | 1 vocal track | | Add Instrumental | Suno | 50 | per call | 1 instrumental | | Voice Conversion | Audimee | 20 | per minute | Converted audio | | Voice Conversion | MusicGPT | 20 | per minute | Converted audio | | Voice Cloning | Suno | 100 | per call | 1 cloned voice | | Voice Cloning | ElevenLabs | 120 | per call | 1 cloned voice | | Voice Cloning | Mureka | 3,750 | per call | 1 cloned voice | | Text to Speech | ElevenLabs | 80 | per 1,000 characters | Speech audio | | Harmony Generation | Audimee | 30 | per call | Harmonies | ## Stems & Cleanup | Action | Provider | Credits | Unit | Output | | -------------------------------------------- | ----------------- | ------- | ---------- | -------------------------- | | Stem Split | LALAL.AI / Demucs | 20 | per minute | Vocal + instrumental stems | | Stem Split | Suno | 30 | per call | Vocal + instrumental stems | | Stem Split | MusicGPT | 20 | per call | Vocal + instrumental stems | | Stem Split | Mureka | 50 | per call | Vocal + instrumental stems | | Multi-stem Split | LALAL.AI / Demucs | 40 | per minute | 6 stems | | All-stems Bundle | LALAL.AI / Demucs | 40 | per minute | All stems | | Advanced Stem Split | Vocuno | 30 | per call | Advanced stems | | Full Stem Split | Vocuno | 60 | per call | Full stem set | | Advanced Stem Split | Suno | 60 | per call | Advanced stems | | Audio Cleanup (de-reverb, de-noise, de-echo) | MusicGPT | 20 | per call | Cleaned audio | ## Lyrics & Writing | Action | Credits | Unit | Output | | ------------------ | ----------------- | -------- | --------------------- | | Generate Lyrics | 10 (15 with Suno) | per call | 1 set of lyrics | | Optimize Lyrics | 5 | per call | Improved lyrics | | Timestamped Lyrics | 10 | per call | Synced lyrics | | Boost Music Style | 10 | per call | Enhanced style prompt | ## Audio Tools | Action | Provider | Credits | Unit | | ------------------- | ---------------------- | ------- | -------- | | Capture Audio | — | 10 | per call | | Stem-to-MIDI | Suno | 20 | per call | | Song Analysis | Vocuno | 10 | per call | | Song Analysis | Mureka | 100 | per call | | Sound Generator | Suno (default) | 30 | per call | | Sound Generator | MusicGPT | 40 | per call | | Sound Generator | ElevenLabs / WaveSpeed | 60 | per call | | Audio Mastering | — | 30 | per call | | Apply Mixing Preset | — | 8 | per call | ## Agent Agent and Mixing Agent messages are metered by the actual AI usage of your message (all tool rounds included), so complex requests cost more than simple ones. As a baseline, a typical Agent message costs around 5 credits and a Mixing Agent message around 25 credits — plus the normal credit cost of any tools the agent runs for you (song generation, stem split, etc.). ## Free tools Several tools cost no credits at all: the file converter, BPM detector, chord finder, audio recognition, audio to MIDI, creation prompts, and the whole practice suite (online tuner, pitch detector, vocal range finder, metronome, tap BPM, and the BPM/note calculators). ## How "per minute" works Actions priced **per minute** charge based on the duration of the audio you submit, rounded up to the nearest minute. For example, splitting a 3:20 track costs `4 × 20 = 80` credits. ## Frequently asked questions You can still access your library and finished tracks, but new generations will be paused until you top up or your plan renews. Credit packs are available from 1,500 credits ($10) up to 214,000 credits ($1,000). No. If a generation fails on our side, the credits are automatically refunded to your balance. Models like Vocuno premium, ElevenLabs, MiniMax and Lyria 3 have higher underlying provider costs, so they use more credits per generation. You can always pick Suno or MusicGPT for the most credit-efficient results. Yes — your remaining balance and recent usage are visible in your account settings. Studio plan members also get a dedicated usage dashboard. # Distribute Your Music to Streaming Platforms Source: https://support.vocuno.com/distribute/overview Release finished tracks to Spotify, Apple Music, and all major platforms from Vocuno. Manage metadata, track releases, and distribute — no third-party needed. Vocuno includes built-in music distribution so you can go from finished track to streaming platforms without leaving the app. Distribution is included with every paid plan, and you retain 100% of the rights to everything you create and release. Step-by-step guide to publishing your first song to streaming platforms. See what's included in each plan. ## What's included Vocuno Distribution is built directly into the platform — no third-party distributor account or separate subscription needed. Release to Spotify, Apple Music, Amazon Music, YouTube Music, Tidal, and more in one submission. Submit your track with a single action. Vocuno handles the delivery to each platform automatically. Set your track title, artist name, album art, genre, release date, and ISRC details before submitting. Monitor the status of your releases and see when they go live on each platform. You own everything you create on Vocuno. All plans include a commercial license. Link your release to your existing Spotify artist profile so it lands on the right page. A commercial license is required to distribute and monetize your music. All Vocuno plans include a commercial license for tracks you create on the platform. ## Before you distribute Make sure your track is ready before submitting: * Export your final mix as a high-quality MP3 or WAV from the Studio * Prepare cover artwork (minimum 3000 × 3000 px, JPEG or PNG) * Have your release date, genre, and artist name ready * Review the track once more — changes after submission may not be possible until the release is live Use the Vocuno Studio to do a final quality check on your mix before distributing. Listen on headphones and check for clipping, balance issues, or unwanted noise. # Release Your Track to Spotify and Apple Music Source: https://support.vocuno.com/distribute/releasing-a-track Step-by-step guide to releasing a finished Vocuno track to Spotify, Apple Music, and all major streaming platforms — from export to going live. Once your track is finished and mixed in the Vocuno Studio, you can release it to all major streaming platforms directly from Vocuno. Distribution is included with every paid plan. Open your song in the **Studio DAW** and do a final check on your mix. When you're happy, export it as a high-quality MP3 or WAV. This will be the master file delivered to streaming platforms. Navigate to the **Distribution** section in your Vocuno dashboard. Click **New Release** to begin the submission flow. Upload your exported audio file and fill in the required metadata: * **Track title** — The name as it will appear on streaming platforms * **Artist name** — Your artist or band name * **Genre** — Primary genre for the track * **Release date** — Set a future date to schedule the release, or choose immediate * **Cover artwork** — Upload a square image (minimum 3000 × 3000 px, JPEG or PNG) * **ISRC** — Vocuno can generate an ISRC code for your track automatically Select the streaming platforms you want to distribute to. By default, Vocuno submits to all major platforms: Spotify, Apple Music, Amazon Music, YouTube Music, Tidal, and more. Review all details, then click **Submit Release**. Vocuno delivers your track to each platform. Processing typically takes 1–5 business days depending on the platform. Monitor your release in the Distribution dashboard. You'll see the delivery status for each platform and a confirmation when your track goes live. ## Metadata tips Getting your metadata right ensures your music is discoverable and correctly attributed. | Field | Notes | | ------------ | ---------------------------------------------------------------------------------------------------- | | Track title | Use your official release title. Avoid adding "(Official Audio)" or similar — platforms handle that. | | Artist name | Use your artist name consistently across all releases. | | Genre | Choose the primary genre. Some platforms support a secondary genre. | | Cover art | Must be square, minimum 3000 × 3000 px. Text-only artwork may be rejected by some platforms. | | Release date | Allow at least 3 business days for Spotify and Apple Music delivery. | Once a release is live on streaming platforms, changing core metadata (title, artist name, ISRC) may require re-submitting the release. Double-check everything before you submit. ## Frequently asked questions Most platforms process new releases within 1–5 business days. Spotify and Apple Music typically take 2–3 business days. To ensure your release is available on a specific date, submit at least 5 business days in advance. Yes. Vocuno does not take a percentage of your streaming royalties. You keep all revenue generated by your distributed tracks. Distribution is included in your Vocuno subscription. Minor metadata changes (like fixing a typo in the title) can sometimes be made after release. Audio file changes require withdrawing and re-submitting the release. Contact Vocuno support for help with post-release changes. Yes. All tracks created on Vocuno come with a commercial license. You own the rights to your creations and can distribute and monetize them. Review the terms of service of the underlying AI providers (Suno, MusicGPT) for any platform-specific licensing details. Yes — an active paid subscription is required to submit releases. Your already-released tracks stay live even between plan changes. Every distributed track also shows up on the [Listen](/listen/overview) community feed with a "created with Vocuno" badge, complete with stream counts and a comment section. # General Tools FAQ Source: https://support.vocuno.com/faq Quick answers about Vocuno's general tools — Create Song, Stems, Lyrics, the pipelines, and the Toolbox. Quick answers about the tools in the **General Tools** section. For questions about the platform itself, plans, or distribution, see the [General FAQ](/faq/general). [Create Vocals](/create/create-vocals) generates a full song from scratch. [Add Vocals to Track](/create/add-vocals-to-track) lays AI vocals over your instrumental. [Add Instrumental](/create/add-instrumental) builds a backing track under your vocal. [Transform Vocals](/create/transform-vocals) re-sings a vocal in a different voice. [Voice Conversion](/create/voice-conversion-1) directly swaps the voice on existing vocals. Voice Conversion is one-shot — fastest, keeps your original phrasing exactly. Transform Vocals re-generates the take from scratch using transcribed lyrics, which often sounds more natural for full performances. Start with Vocuno's advanced splitter or LALAL.ai (the widest custom-stem support — drums, bass, guitar, etc.). Moises, BandLab, and LANDR are worth trying when a mix separates poorly. Suno's stem split is only available on tracks generated with Suno inside Vocuno. ElevenLabs, MiniMax, and Lyria 3 have higher provider costs and use more credits per generation. Suno and MusicGPT are the most credit-efficient. Full breakdown on the [Credit Costs](/credit-costs) page. Most tools accept MP3, WAV, FLAC, AAC, OGG, M4A, Opus, and AIFF. Clean, dry recordings give the best results across stem separation, voice conversion, and de-reverb. No — credits are auto-refunded when a generation fails on our side. Everything lands in your library and stays available across the app — you can pull any track into the [Studio](/using-the-studio) or send it to [Distribution](/distribute/overview). Yes! All your deleted tracks stay in the trash for 30 days after initial deletion. To access the trash you can go to your projects and click on trash. Screenshot 2026 04 19 At 12 49 09 # Copyright and Licensing for AI-Generated Music Source: https://support.vocuno.com/faq/copyright-and-licensing Understand who owns AI-generated music on Vocuno, what the commercial license covers, and how to check copyright before releasing your tracks. When you create music on Vocuno, you own 100% of what you produce. All plans include a commercial license, which means you can release, distribute, and monetize your tracks. This page explains the key licensing concepts you should know before releasing your music. You do. All tracks you generate on Vocuno are yours. Vocuno does not claim any ownership over your creations. You retain full rights to use, distribute, and monetize your music. The commercial license included in all Vocuno plans allows you to release, distribute, sell, and monetize music created on the platform. This includes uploading to Spotify, Apple Music, YouTube, licensing your music for sync, and selling beats or tracks. Vocuno does not require you to credit the platform in your releases. Check the terms of the individual AI providers (Suno, MusicGPT, ElevenLabs) for their specific attribution requirements, as these may vary. Yes. The commercial license covers use in commercial projects — ads, sync licenses, YouTube monetization, streaming revenue, and more. The Pro plan is recommended for commercial use given the higher credit allocation, priority processing, and unlimited distribution. Vocuno routes tasks through third-party AI engines including Suno, Udio, Mureka, MusicGPT, MiniMax, LALAL.ai, ElevenLabs, and Audimee. Each provider has its own terms of service regarding commercial use. For high-stakes commercial projects, review the terms of the relevant provider directly. Making a [cover](/create/cover-remix) for personal listening or sharing on Vocuno is fine. Releasing a cover of a copyrighted song to streaming platforms requires a mechanical license for the underlying composition (services like distributors' cover-licensing programs handle this per territory). Original songs you generate need no such license. The stem separator works on any audio file you upload. However, using separated stems from copyrighted recordings in your own commercial releases may infringe copyright. You need to own or have licensed the original recording before using its stems commercially. The tool itself is neutral — responsibility for how you use the output rests with you. Before using any existing audio in your projects, check ownership through: * **ASCAP, BMI, or SESAC** databases for US-registered works * **PRS for Music** (UK) or equivalent collecting society in your country * The **US Copyright Office** public catalog at copyright.gov * Spotify and YouTube's content ID tools to see if a track has claims attached When in doubt, assume the work is copyrighted and seek permission or use original content. Copyright law around AI-generated content is evolving. In most jurisdictions, purely AI-generated content without sufficient human creative input may not be eligible for copyright protection. However, tracks where you provide lyrics, creative direction, editing, and arrangement choices may qualify. Consult a music attorney for advice specific to your situation and jurisdiction. Voice-converted audio can be used in your projects subject to the terms of the underlying voice model provider (MusicGPT/ElevenLabs). Review their commercial use terms for specifics. Also ensure you have the rights to the original vocal recording you're converting. This page provides general information and is not legal advice. For specific questions about your rights and obligations, consult a qualified music or intellectual property attorney. # Frequently Asked Questions about Vocuno Source: https://support.vocuno.com/faq/general Answers to the most common questions about Vocuno — credits, plans, AI engines, generation quality, supported formats, and how the platform works. This page covers the most frequently asked questions about using Vocuno. If you don't find what you're looking for here, you can reach the Vocuno team directly via the support chat in the app. Vocuno is an AI-powered music creation platform that combines the best AI music engines — Suno, Udio, Mureka, MusicGPT, MiniMax, LALAL.ai, ElevenLabs, Audimee, and Lyria 3 — in one subscription. You can generate full songs from text prompts, cover and remix existing songs, add AI vocals to your beats, separate stems, clone voices, mix in a browser DAW, and distribute your music to streaming platforms, all without leaving the app. No. Vocuno is designed to work for everyone — from complete beginners to professional producers. The Vocuno Agent lets you describe what you want in plain language and handles the entire pipeline automatically. For more control, the Studio DAW gives you hands-on multi-track editing. Credits are the universal currency across all Vocuno tools. Each action — generating a song, separating stems, converting a voice — costs a set number of credits (see [Credit Costs](/credit-costs)). Your credits refresh every month with your plan. Unused monthly credits do not roll over, but bonus credits (from packs, referrals, or support) never expire. Yes — credit packs are available on demand, from 1,500 credits ($10) up to 214,000 credits ($1,000), with bonus credits on larger packs. See [Billing & Subscriptions](/billing-and-subscriptions). Every plan includes access to all providers: Suno, Udio, Mureka, MusicGPT, MiniMax, LALAL.ai, Audimee, ElevenLabs, and Lyria 3. Vocuno routes each task to the best provider automatically — you don't need separate subscriptions to any of them. A simple song generation usually previews in under a minute and finishes within a few minutes. Full multi-step pipelines (like Create Vocals in Clean mode) take 3–5 minutes, with real-time progress as each step completes. Most Vocuno tools accept MP3, WAV, FLAC, AAC, OGG, and other common audio formats. For voice conversion and stem separation, clean recordings (especially dry vocals) give the best results. Yes — there's a native [iOS app](/mobile-app) for listening, discovery, and song creation, and the full web app works in any modern mobile browser. The Studio DAW is best experienced on a desktop or laptop for editing precision. **Starter** ($19/mo, $18/mo billed annually) includes 1,500 monthly credits. **Pro** ($49/mo, $34/mo annually) includes 10,000 credits. **Studio** ($99/mo, $69/mo annually) includes 30,000 credits plus an opt-in Unlimited creation mode and a 10,000-credit monthly Marketplace allowance. All plans include every AI engine, the Studio DAW, and the Vocuno Agent — see [Billing & Subscriptions](/billing-and-subscriptions). Yes. You can upgrade, downgrade, or cancel at any time. When upgrading, extra credits are added immediately. When downgrading, the change takes effect at your next billing cycle. There are no lock-in fees or hidden charges. The [Vocuno Marketplace](/marketplace/overview) is a sample-pack storefront — buy packs from other creators, or open a creator shop and sell your own with payouts via Stripe Connect. Only if you publish it. Your library is private by default; tracks appear on the [Listen](/listen/overview) community feed only when you release them through Distribution. You can reach the Vocuno team via the support chat inside the app, or by email at [contact@vocuno.com](mailto:contact@vocuno.com). Priority support is included with all paid plans. # Welcome to Vocuno! Source: https://support.vocuno.com/introduction Learn what Vocuno is, which AI engines power it, and how songwriters, producers, and content creators can build full tracks in minutes. Welcome To Vocuno Vocuno is an all-in-one AI music creation platform that connects you to the best AI music engines: Suno, Udio, Mureka, MusicGPT, MiniMax, LALAL.ai, ElevenLabs, Audimee, and Lyria 3 — through a single subscription. \ \ Instead of juggling separate tools and logins, you describe what you want and Vocuno routes each step of the pipeline to the right provider automatically.\ \ The result is a polished, export-ready track without needing a recording studio or music production experience. It really is the best in class tool for music producers and beginners all alike. ## What you can do with Vocuno Vocuno covers every stage of music creation, from the first idea to distribution on streaming platforms. * **Use the Vocuno Agent:** Chat with Vai (the Vocuno AI). Vai has access to all the tools on the platform and is the most powerful and modern music agent on the web. It has access to all the different providers (suno, elevenlabs etc) but also to specialized production tools. * **Generate full songs**: Turn a text prompt or your own lyrics into a complete track with AI vocals and instrumentals. Vocuno handles melody, arrangement, and production automatically. * **Write AI lyrics**: Get verse, chorus, and bridge suggestions based on a theme, mood, or genre. Edit the output before generating your song. * **Add or transform vocals**: Upload an instrumental and add AI-generated vocals on top, or convert existing vocals into a different voice style using ElevenLabs and Audimee. * **Separate stems**: Split any song into its individual components — vocals, drums, bass, and instruments — for remixing, sampling, or re-mixing with LALAL.ai. * **Mix in the Studio DAW**: Fine-tune your track in a browser-based multi-track editor with AI mixing, beat grid, and WAV or MP3 export. * **Distribute to streaming platforms**: Release your finished music to Spotify, Apple Music, and other major platforms directly from Vocuno. * **Share and discover on Listen**: Publish tracks to the community feed, follow artists, build playlists, and join the conversation with song comments. * **Buy and sell sample packs**: Browse the Vocuno Marketplace for sample packs from other creators, or open a creator shop and sell your own. * **Create on the go**: The Vocuno iOS app brings the Listen feed, your library, and song creation to your iPhone. ## AI engines included Every Vocuno plan gives you access to all of these providers. Vocuno selects the best engine for each task automatically, you will never need separate subscriptions ever again. | Engine | What it powers | | -------------- | -------------------------------------------------------------------- | | **Suno** | Full-song generation from text prompts (V5.5, V5, V4.5) | | **Udio** | High-fidelity song generation | | **Mureka** | Song generation, vocal cloning, and song analysis (V9, V8, V7.6, O2) | | **MusicGPT** | Multi-engine song generation and arrangement | | **MiniMax** | High-quality audio synthesis | | **LALAL.ai** | Stem separation, dereverb | | **ElevenLabs** | AI voice generation, conversion, and text-to-speech | | **Audimee** | Voice style transformation | | **Lyria 3** | Powerful music generation model by Google | ## Who Vocuno is for Vocuno is built for anyone who wants to create music with AI — whether you have years of production experience or none at all. * **Songwriters** — Hear your lyrics as a finished song in minutes. Use the AI lyrics generator to develop ideas, then generate a full track without touching a DAW. * **Producers** — Add AI vocals to your beats, separate stems from reference tracks, and use the Studio DAW to mix everything in the browser. * **Content creators** — Generate royalty-free background music, voiceovers, and original tracks for videos, podcasts, and social media. All plans include a commercial license. ## Explore the docs Turn any text prompt or lyrics into a complete song with vocals and instrumentals. Generate verse, chorus, and bridge lyrics for any genre, mood, or theme. Split any track into vocals, drums, bass, and instruments for remixing. Run the full creation pipeline through a single natural-language chat. Mix and arrange your tracks in a browser-based multi-track editor with AI mixing. Release your music to all major streaming platforms with one click. Buy sample packs from other creators or sell your own. Listen, create, and manage your library from your iPhone. # Listen — Discover Music on Vocuno Source: https://support.vocuno.com/listen/overview Discover new tracks and artists, follow creators, build playlists, and publish your own music to the Vocuno community. Browse music ↗️ Listen artist discovery **Listen** is Vocuno's social discovery feed — a place to browse tracks, follow artists, build playlists, and share your own releases with the community. Everything you publish through [Distribution](/distribute/overview) shows up here, with full social stats and stream counts pulled from Spotify, Apple Music, and YouTube. ## What you can do * **Discover tracks and artists** — browse by song, artist, or playlist; trending content surfaces at the top. * **Artist profiles** — view a creator's catalogue, follower count, social links (Spotify, Apple, YouTube, Instagram, TikTok), and verified status. * **Persistent player** — playback continues across pages with a bottom player that has skip, seek, volume, and queue controls. * **Playlists** — explore public playlists, like songs, and follow artists to build a personalised feed. * **Comments** — join the conversation on any published track, right from the song page, feed, or player. * **Your profile** — your published tracks, followed artists, and liked songs are all visible on your public profile at `vocuno.com/listen/profile`. ## Comments Every published track has a comment section, available on the song page, on feed cards, and in the player. You can like comments, and the track's creator gets an **artist badge** on their replies and can **pin one comment** to the top of the thread. If you see something that doesn't belong, use the report option on the comment — repeatedly reported comments are hidden automatically and reviewed by moderation. ## Publishing to Listen Tracks released through [Distribution](/distribute/overview) automatically appear on Listen with a "created with Vocuno" badge. Set up your artist profile (display name, bio, profile image, cover art, genre tags) and your songs become discoverable to the community. ## Frequently asked questions No — anyone can browse Listen, like songs, comment, follow artists, and build playlists. A paid plan is only needed to publish your own music via Distribution. Vocuno aggregates listener stats from Spotify, Apple Music, and YouTube and shows them on track and artist pages with milestone badges (100K, 1M, 10M+). Yes — every artist, song, and playlist has a shareable URL (e.g., `vocuno.com/listen/artist/@yourhandle`). No. Only tracks you submit through [Distribution](/distribute/overview) appear on Listen. Drafts and library tracks remain private. # Marketplace Source: https://support.vocuno.com/marketplace/overview Buy sample packs from Vocuno creators, or open a creator shop and sell your own — with built-in payouts. Browse sample packs ↗️ Vocuno Marketplace The **Vocuno Marketplace** is a storefront for sample packs made by the Vocuno community. Browse and buy packs to use in your own productions, or become a creator and sell packs built from your own Vocuno library. ## Buying packs Browse packs by creator or category, preview the contents, and purchase directly. Purchased packs are delivered as secure downloads tied to your account. **Studio plan** members get a separate 10,000-credit monthly allowance to spend on the Marketplace. ## Selling packs Any creator can open a shop: 1. Go to the creator dashboard at `vocuno.com/marketplace/creator`. 2. Connect a payout account (powered by Stripe Connect) so you can get paid. 3. Upload your pack — cover art plus a ZIP of your samples — or assemble one from tracks and stems in your Vocuno library. 4. Publish. Sales and earnings are tracked in your creator dashboard, and payouts go straight to your connected account. ## Frequently asked questions You can browse without a plan. Buying and selling require an account in good standing; check the creator dashboard for current requirements in your region. Payouts run through Stripe Connect. Once your account is connected, earnings from your sales are transferred automatically. Samples you have the rights to sell — including material you created on Vocuno. Packs go through a review before appearing publicly. # Vocuno for iOS Source: https://support.vocuno.com/mobile-app The Vocuno iPhone app — browse the Listen feed, create songs, and manage your library on the go. The **Vocuno iOS app** brings the core of Vocuno to your iPhone. It's a companion to the web app — sign in with the same account and your library, likes, and follows stay in sync. ## What you can do * **Listen feed** — browse **For You** and **Latest** tabs, search for tracks and artists, and play music with a full-screen player. * **Create songs** — generate new tracks right from your phone in Simple or Custom mode, with a choice of AI models. * **Your library** — access your generated songs, stems, and captures; like tracks and creations. * **Social** — follow artists, view profiles, comment on tracks, and open shared links directly in the app. ## Getting the app The app is available on the App Store for iPhone. Shared Vocuno links (songs, artists, profiles) open directly in the app once it's installed. ## Frequently asked questions The app focuses on listening, discovery, and song creation. The full toolbox — stems, pipelines, Studio DAW, distribution, marketplace — lives on [vocuno.com](https://vocuno.com), and everything you create on mobile is there too. Yes — it's one account and one credit balance across web and mobile. Not yet — Android users can use the web app at vocuno.com, which works well in mobile browsers. # Using the Studio Source: https://support.vocuno.com/using-the-studio Mix, edit, and arrange your tracks in the Vocuno Studio — a browser-based multi-track DAW with BPM detection, beat grid, and WAV/MP3 export. Launch Studio ↗️ The **Vocuno Studio** is a browser-based multi-track DAW for arranging, editing, and mixing the tracks you generate. Pull in stems, vocals, and instrumentals from your library, line them up on the timeline, and export a finished WAV or MP3 — no install, no native plugins. Vocuno Studio session ## Core features * **Multi-track timeline** — import and arrange unlimited tracks with waveform display * **Clip editing** — cut, copy, paste, trim, and delete regions; per-clip gain control * **BPM detection & beat grid** — auto-detect tempo and snap edits to the bar * **Mix controls** — per-track volume, mute, and solo * **Library import** — drag in any generated song, stem, conversion, or capture * **Sessions** — auto-save to Firebase with full restore (track layout, mute state, clips) * **Undo / redo** — full non-destructive editing history * **Export** — render to WAV or MP3 with all your mute and volume settings baked in * **AI tool dock** — run advanced tools without leaving the Studio: audio mastering, the mixing agent, replace section, timestamped lyrics, stem-to-MIDI, sound generator, cover artwork, mashup, and more Studio AI Tools menu ## Typical flow Start a session from a finished song or a stem split, drop additional layers (extra vocals, ad-libs, effects you captured) onto new tracks, line them up on the beat grid, and trim the dead air. When the mix sounds right, export and either download the file or send it straight to [Distribution](/distribute/overview). ## Frequently asked questions No — the Studio runs entirely in the browser. A desktop or laptop is recommended for editing precision. Anything in your Vocuno library — generated songs, stems, voice conversions, captures — plus audio files you upload directly. Sessions auto-save to your account. You can close the tab and come back to the same arrangement later. WAV (lossless) and MP3. Export bakes in mute, solo, and volume settings for every track.