whatmodel.sh / tts / ElevenLabs v3 Alpha
ElevenLabs v3 Alpha
↗ share
+ contribute
ElevenLabs v3 Alpha is a closed-weights text-to-speech model from ElevenLabs, released June 2025.
Catalogue identity notes
Exact figure legend Eleven-v3 (Alpha). Do not relabel Alpha as production v3.
Model information sources
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of ElevenLabs v3 Alpha, out of 148 with a score, then more from ElevenLabs.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 63 |  ZONOS2 8B | 57±2 | local | ||
| 64 |  Supertonic 3 | 55±10 | local | ||
| 65 | ElevenLabs v3 Alpha | 55±9 | comparison only | ||
| 66 |  Higgs Audio V2 | 55±3 | local | ||
| 67 | Fasih-TTS-V1 | 55±10 | local | ||
| more from ElevenLabs | |||||
| 21 | Eleven v3 | 65±1 | api $100.00/M chars | ||
| 30 | Eleven Turbo v2.5 | 64±4 | api $50.00/M chars | ||
| 38 | Eleven Flash v2.5 | 63±2 | api $50.00/M chars | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 69% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| VibeVoice podcast · preference MOS (MIT figure) | 3.37 / 5 ✎ | █·█········█ beats 0/2 | 69% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Microsoft VibeVoice own subje… 69%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Microsoft VibeVoice own subjective evaluation figure | 1 | 69% |
| prior · pull toward the middle | 31% | |
| weighted average | = 54.8 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json