Skip to main content

Text to Speech Tool

Try it now! ↗️
Text to Speech turns a script into spoken audio for voiceovers, narration, spoken-word intros or podcast segments. Results land in the Speech tab of your library.

Providers

Per-1,000 pricing counts each started block of 1,000 characters: a 2,500-character script on ElevenLabs costs 240 credits. See Credit Costs.

How to use it

  1. Paste or write your script. A live counter shows your provider’s limit.
  2. Pick a provider and a voice, and preview voices until one fits.
  3. Adjust the provider’s options (below).
  4. Generate.

ElevenLabs options

  • Model: Multilingual v2 (default, best quality), Turbo v2.5, or Flash v2.5 (fastest).
  • Voice settings: stability, similarity, style, speed and speaker boost.
  • Output format: MP3 128 kbps (default), MP3 192 kbps, Opus, PCM or µ-law.

Suno Speech options

Suno returns two spoken variations of your script.
  • Tone: describe the delivery, pacing, mood and setting.
  • Voice gender: any, male or female.
  • Variety: from Off to Max.
  • Background music: on by default, turn it off for a dry voice.

Frequently asked questions

Yes. Clone it first with Voice Cloning (ElevenLabs IVC) and it appears in your ElevenLabs voice list, marked Saved.
Most providers speak many languages. Write your script in the target language and pick a voice that suits it. For less common languages, try OmniVoice.
Yes. Anything in your Speech library tab can be pulled into the Studio as a track, or used in any tool that accepts library audio.