Skip to main content

Documentation Index

Fetch the complete documentation index at: https://support.vocuno.com/llms.txt

Use this file to discover all available pages before exploring further.

Talk to Vai

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 28+ tools across every part of the platform: song generation (Suno, MusicGPT, MiniMax, ElevenLabs, Lyria 3), stem separation, voice conversion, lyrics generation, FFmpeg 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.

​
Skills

Skills are pre-built multi-step workflows Vai can trigger when you ask for something specific. The built-in cover skill, for example, takes a song name, fetches the lyrics, captures audio from YouTube, separates stems, and runs the cover pipeline end-to-end — all from a single message like “cover Wonderwall in a female voice”.

​
Inputs and credits

You can type prompts or hold the mic button to dictate them. Each agent message costs 5 credits, and any tools the agent runs (song generation, stem split, etc.) deduct their normal credit cost — see 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.