The Known Good Updated 29 Jul 2026

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.

Text Image Video Speech

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
42 models rated Ratings captured 29 Jul 2026 Source: TTS Arena
# Model Creator Elo 95% CI Votes Known Good Index
1 Vocu V3.0 Unknown 1,564
4 Luna TTS Unknown 1,563
2 CastleFlow v1.0 Unknown 1,561
3 Inworld TTS MAX Unknown 1,558
6 Papla P1 Unknown 1,550
8 Luck Dolphin Unknown 1,548
7 Luck Dolphin Turbo Unknown 1,547
5 Inworld TTS Unknown 1,543
9 star-june-2026 Unknown 1,538
11 MiniMax Speech 2.8 HD MiniMax 1,536
12 Gradium TTS Unknown 1,532
10 Hume Octave Hume AI 1,529
13 Lightning v3.1 Pro Unknown 1,527
29 Deepdub eTTS 3.2 Unknown 1,525
17 MiniMax Speech 2.8 Turbo MiniMax 1,524
22 Typecast SSFM 3.0 Unknown 1,521
28 Cartesia Sonic 2 Cartesia 1,520
19 Hithink Speech 2.6 Unknown 1,519
15 MiniMax Speech 2.6 HD MiniMax 1,518
18 OpenAudio S2 Unknown 1,517
23 Inworld TTS 1.5 MAX Unknown 1,516
14 Eleven Turbo v2.5 ElevenLabs 1,514
27 MiniMax Speech 2.6 Turbo MiniMax 1,514
16 MiniMax Speech 02 HD MiniMax 1,513
26 OpenAudio S1 Unknown 1,513
30 Eleven v3 ElevenLabs 1,510
21 Eleven Flash v2.5 ElevenLabs 1,508
20 Eleven Multilingual v2 ElevenLabs 1,508
25 MiniMax Speech 02 Turbo MiniMax 1,505
24 Parmesan Unknown 1,505
31 Voice.ai Text to Speech V1 Unknown 1,501
32 Tontaube V0 Unknown 1,500
33 Chatterbox Unknown 1,481
34 Kokoro v1.0 Unknown 1,478
35 Magpie Research Preview Unknown 1,475
36 NLS Pre V1 Unknown 1,462
37 NeuTTS Max Unknown 1,440
40 Silk Mulberry 1.5 Unknown 1,424
39 Maya 1 Unknown 1,412
38 Magpie Multilingual Unknown 1,407
42 Veena Unknown 1,365
41 Wordcab TTS Unknown 1,361
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.