- Services
ElevenLabs builds closed-source text-to-speech and voice cloning models. Their multilingual voice models are the most widely deployed commercial TTS APIs.
Visit ElevenLabsModels tracked
2
Open weight
0
API only
2
Avg score
65.3
Top benchmark
100.0
TTS Arena
Total HF downloads
—
First release
Aug 2023
Latest release
Mar 2026
Ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | Eleven v3API | audio | BB67.8 | — | Mar 2026 |
| 2 | Eleven Multilingual v2API | audio | BB62.9 | — | Aug 2023 |
The strongest model from this provider in each modality. Click a card to open the model page.
Audio
Eleven v3
How this provider’s catalog splits across text, image, video, audio, embedding, and decision models.
When each model shipped, newest first.
Mar 14
Aug 22
Closed-source models accessed through ElevenLabs’s API.
API pricing is per million tokens unless noted otherwise.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | Eleven v3API | audio | BB67.8 | — | Mar 2026 |
| 2 | Eleven Multilingual v2API | audio | BB62.9 |
ElevenLabs ships 2 models that we track. Of those, 0 are open weight and 2 are accessed through their API.
It depends on the model. See the open-weight section above for models you can run locally, and the API-only section for closed models priced per token.
By composite score, Eleven v3 is currently the top ElevenLabs model in our directory. Composite score blends benchmarks, popularity, efficiency, and versatility.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Open Directory
See every release in a family side by side, with a timeline and a leaderboard. Useful when you have already picked a series and want the right size.
Composite grades across this provider’s catalog. Higher is better, blending benchmarks, popularity, and efficiency.
| — |
| Aug 2023 |
