| Model | Max duration | Sample rate | Channels | Languages | Genres |
|---|---|---|---|---|---|
| Eleven English Speech to Speech v2 | — | — | — | en | — |
| Eleven Multilingual Speech to Speech v2 | — | — | — | 29 | — |
| Eleven Multilingual Text to Voice v2 | — | — | — | 29 | — |
| Eleven Realtime v1 Max | — | — | — | — | — |
| Eleven Realtime v1 Mini | — | — | — | — | — |
| Eleven Text to Sound v2 | — | — | — | — | — |
| Eleven Text to Sound v3 | — | — | — | — | — |
| Eleven Text to Voice v3 | — | — | — | — | — |
| Eleven Music v1 | — | — | — | — | — |
| Eleven Music v2 | — | — | — | — | — |
| Eleven Music v2.5 | — | — | — | — | — |
/v1/models/elevenlabs/music_v2_5Music generation from text prompts, composition plans and previously generated songs, with improved prompt adherence.