ElevenLabs v3 Text to Speech

ElevenLabs v3 Text to Speech · ElevenLabs — Text to audio · 21 voices. Call it through one queue API and pay for the options you pick.

modellane/elevenlabs-v3-text-to-speech · Text to audio · ElevenLabs

Text to audio model: 21 voices.

Vendor
ElevenLabs
Task
Text to audio
Output
Audio
Price
Based on text length

Input parameters

  • Text text — required, at most 5000 characters The text fed into the generation.
  • Voice voice — optional, options: hpp4J3VqNfWAUOO0d1Us, CwhRBWXzGAHq8TQ4Fs17, EXAVITQu4vr4xnSDxMaL, FGY2WhTYpPnrIDTdsKH5, IKne3meq5aSn9XLyUdCD, JBFqnCBsd6RMkjVDRZzb, N2lVS1w4EtoT3dr4eOWO, SAz9YHcvj6GT2YYXdXww, SOYHLrjzK2X1ezoPC6cr, TX3LPaxmHKxFdv7VOQHJ, Xb7hH8MSUJpSbSDYk0k2, XrExE9yKIg1WjnnlVkGX, bIHbv24MWmeRgasZH58o, cgSgspJ2msm6clMCkdW9, cjVigY5qzO86Huf0OWal, iP95p4xoKVk53GoZ742B, nPczCjzI2devNBz1zQrb, onwK4e9ZLuTAKqWW03F9, pFZP5JQG7iQjIQuC4Bku, pNInz6obpgDQGcFmaJgB, pqHfZKP75CvOlQylNhV4 The voice profile to use.
  • Stability stability — optional, default: 0.5, range: 0–1
  • Apply text normalization apply_text_normalization — optional, options: Auto, On, Off
  • Language code language_code — optional

Output and retention

The generated file and your input are kept for seven days and then deleted.

Queue API

Submit to the queue: POST /v1/queue/modellane/elevenlabs-v3-text-to-speech

Status, result, cancellation and error codes work the same for every model; see the API docs.

Playground

Everything on this page is public; you need an account to run the model.