Speech Arena
Elo ratings from blind pairwise votes: a human is shown two anonymous outputs for the same prompt and picks the better one. The votes are collected and published by TTS Arena — we ingest the ratings, we do not run the votes and we do not adjust them.
Speech Arena
Human preference rating from blind pairwise votes, ingested from TTS Arena
Text to Speech Arena
Elo from blind pairwise preference votes, collected and published by TTS Arena. Higher is better. We ingest these ratings; we do not run the votes and we do not run our own evaluations.
The Known Good
Text to Speech Arena — full ranking
46 models rated
Ratings captured 4 Sep 2026 Source: TTS Arena
| # | Model | Creator | Elo | 95% CI | Votes | Known Good Index |
|---|---|---|---|---|---|---|
| 2 | UT uni-tts-preview | Unknown | 1,625 | — | — | — |
| 2 | UT U2-TTS | Unknown | 1,625 | — | — | — |
| 2 | Au Aurora | Unknown | 1,590 | — | — | — |
| 3 | LT Luna TTS | Unknown | 1,586 | — | — | — |
| 3 | LD Luck Dolphin | Unknown | 1,577 | — | — | — |
| 1 | VV Vocu V3.0 | Unknown | 1,565 | — | — | — |
| 5 | DE Deepdub eTTS 3.2 | Unknown | 1,564 | — | — | — |
| 3 | CV CastleFlow v1.0 | Unknown | 1,562 | — | — | — |
| 4 | IT Inworld TTS MAX | Unknown | 1,562 | — | — | — |
| 7 | LD Luck Dolphin Turbo | Unknown | 1,560 | — | — | — |
| 8 | SJ star-june-2026 | Unknown | 1,554 | — | — | — |
| 6 | PP Papla P1 | Unknown | 1,551 | — | — | — |
| 7 | IT Inworld TTS | Unknown | 1,543 | — | — | — |
| 10 | LV Lightning v3.1 Pro | Unknown | 1,541 | — | — | — |
| 9 | GT Gradium TTS | Unknown | 1,538 | — | — | — |
| 12 | OS OpenAudio S2 | Unknown | 1,537 | — | — | — |
| 13 |
MiniMax Speech 2.8 HD
|
MiniMax | 1,532 | — | — | — |
| 11 | Hu Hume Octave | Hume AI | 1,527 | — | — | — |
| 14 |
MiniMax Speech 2.6 Turbo
|
MiniMax | 1,525 | — | — | — |
| 17 |
MiniMax Speech 2.8 Turbo
|
MiniMax | 1,518 | — | — | — |
| 21 | IT Inworld TTS 1.5 MAX | Unknown | 1,515 | — | — | — |
| 20 |
MiniMax Speech 2.6 HD
|
MiniMax | 1,514 | — | — | — |
| 15 |
MiniMax Speech 02 HD
|
MiniMax | 1,513 | — | — | — |
| 23 | TS Typecast SSFM 3.0 | Unknown | 1,512 | — | — | — |
| 27 | Ca Cartesia Sonic 2 | Cartesia | 1,511 | — | — | — |
| 18 |
Eleven Turbo v2.5
|
ElevenLabs | 1,510 | — | — | — |
| 24 | OS OpenAudio S1 | Unknown | 1,510 | — | — | — |
| 19 |
Eleven Flash v2.5
|
ElevenLabs | 1,509 | — | — | — |
| 16 |
Eleven Multilingual v2
|
ElevenLabs | 1,509 | — | — | — |
| 26 | HS Hithink Speech 2.6 | Unknown | 1,508 | — | — | — |
| 28 |
Eleven v3
|
ElevenLabs | 1,506 | — | — | — |
| 22 |
MiniMax Speech 02 Turbo
|
MiniMax | 1,506 | — | — | — |
| 25 | Pa Parmesan | Unknown | 1,504 | — | — | — |
| 31 | TV Tontaube V0 | Unknown | 1,483 | — | — | — |
| 29 | Ch Chatterbox | Unknown | 1,482 | — | — | — |
| 32 | VA Voice.ai Text to Speech V1 | Unknown | 1,480 | — | — | — |
| 30 | KV Kokoro v1.0 | Unknown | 1,479 | — | — | — |
| 33 | MR Magpie Research Preview | Unknown | 1,476 | — | — | — |
| 36 | NP NLS Pre V1 | Unknown | 1,465 | — | — | — |
| 34 | NM NeuTTS Max | Unknown | 1,441 | — | — | — |
| 36 | SM Silk Mulberry 1.5 | Unknown | 1,424 | — | — | — |
| 37 | M1 Maya 1 | Unknown | 1,413 | — | — | — |
| 35 | MM Magpie Multilingual | Unknown | 1,408 | — | — | — |
| 38 | FV Fluxions Vui | Unknown | 1,393 | — | — | — |
| 40 | Ve Veena | Unknown | 1,366 | — | — | — |
| 39 | WT Wordcab TTS | Unknown | 1,363 | — | — | — |
The Known Good
How to read Elo. A rating is only meaningful against the population that produced it: a model's number in one
arena cannot be compared to its number in another, and a rating built on a few hundred votes moves far more than one
built on tens of thousands — the 95% confidence interval is the honest guide to that. Elo measures which output a
person preferred, not whether it was correct; for correctness see the
evaluations and the
Known Good Index, which does not include Elo. Ratings are
ingested from TTS Arena and are published under the source's own terms — see
attribution.