ElevenLabs
Eleven v3 text to speech
Eleven v3 turns a script into expressive speech in over 70 languages. Its changes in emphasis and emotion suit character performances and dramatic narration.
API model ID
elevenlabs/eleven_v3Best for
- Voice a character who moves from whispers to shouts
- Record alternate readings of a trailer voice-over
More examples
Technical details
Read the model documentation- API model ID
elevenlabs/eleven_v3- Provider
- ElevenLabs
- Modality
- Audio
- Input
- Text
- Output
- Speech audio
- Endpoint
POST /v1/audio/speech- Response formats
- mp3 · pcm · opus, or an ElevenLabs output format such as mp3_44100_128
- API constraints
- ElevenLabs offers no speed control on this model.
Request parameters
inputstring · RequiredWhat to say.
text, within the model's character limit (above)
voicestring · RequiredThe OpenAI-style names are mapped to ElevenLabs voices (alloy is Rachel, ash is Domi, coral is Aria, …); any other value is passed on as a voice id.
an ElevenLabs voice id, or alloy · amber · ash · august · blue · coral · lily · onyx · sage · verse
response_formatstring · Optional · Default: pcm (44.1 kHz)mp3 is 44.1 kHz at 128 kbps and opus 48 kHz at 128 kbps. Send mp3 for a playable file: the default is raw PCM.
mp3 · pcm · opus, or an ElevenLabs output format such as mp3_44100_128
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per 1K characters | $0.096 |
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue