Eleven v3
ElevenLabs
- Released
- -
- Data date
- September 24, 2026
- Model class
- Languages
- Access
Eleven v3 is ElevenLabs’ expressive text-to-speech model for multilingual, multi-speaker output. The provider documents more than 70 languages, a 5,000-character text limit, and a Text to Dialogue API for conversations with multiple voices. Its value lies in emotional range and contextual delivery, not general audio reasoning. For narration, character voices, and text-generated dialogue, that specialization is the point.
ElevenLabs now describes v3 as a previous-generation synthesis model. ElevenLabs now lists Eleven v4 and Eleven v4 Turbo as newer speech-synthesis models. The separate Eleven v3 Conversational profile targets real-time speech synthesis over a Text to Dialogue WebSocket. Choose between them by transport and workflow, not just by the shared v3 label.
Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
| Specification | Value and source |
|---|---|
| Model class | Text-to-speechSource |
| Access | APISource |
| API model ID | eleven_v3Source |
| Input | TextSource |
| Output | AudioSource |
| Task | Expressive speech generationSource |
| Supported details | Multi-speaker output in more than 70 languagesSource |
| Text input | Up to 5,000 charactersSource |
| Languages | Over 70 languagesSource |
| Dialogue | Multi-speaker dialogue through the Text to Dialogue APISource |
Popularity
Popularity
39.3 / 100
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Additional source | ElevenLabs model documentation (retrieved September 24, 2026) · ElevenLabs model documentation · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |