Skip to content
IFAI

Model rankings

1260 models · 5 boards · 2 sources

‹
Week of June 1, 2026
July 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changesMay 18, 202616 changesMay 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated June 7, 2026

Best voice
Fun-Realtime-TTSAlibaba1,231Score
Best open model
Fish Audio S2 ProFish Audio1,122Score
Best from China
Fun-Realtime-TTSAlibaba1,231Score
Top three by Score
1Fun-Realtime-TTSAlibaba1,231
2Gemini 3.1 Flash TTSGoogle1,229
3xAI Text to SpeechxAI1,208
Top three open models
1Fish Audio S2 ProFish Audio · #19 overall1,122
2Step Audio EditX (Mar 2026)StepFun · #22 overall1,112
3Voxtral TTSMistral · #36 overall1,080
This week's changes
Fun-Realtime-TTSSpeech · #1New
claude-opus-4-8-thinkingCoding · #2New
Cosmos3-Super-Text2Image (agentic)Image · #5New
minimax-m3Coding · #6New
Krea 2 MediumImage · #7New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1NewFun-Realtime-TTSClosedAlibaba1,231±17
2▼ 1Gemini 3.1 Flash TTSClosedGoogle1,229±15
3▲ 2xAI Text to SpeechClosedxAI1,208±17
4▼ 1Sonic 3.5ClosedCartesia1,204±16
5▼ 3Realtime TTS-2 - Research PreviewClosedInworld1,204±15
6▼ 2Realtime TTS 1.5 MaxClosedInworld1,201±14
7NewAsync Flash v1.5ClosedAsync1,186±17
8▼ 1StepAudio 2.5 TTSClosedStepFun1,181±16
9—Speech 2.8 HDClosedMiniMax1,175±12
10▼ 2Eleven v3ClosedElevenLabs1,173±12
11NewAsync Pro v1.0ClosedAsync1,165±16
12▼ 2Inworld TTS 1 MaxClosedInworld1,158±13
13▼ 2Realtime TTS 1.5 MiniClosedInworld1,152±13
14—Speech 2.8 TurboClosedMiniMax1,151±12
15▼ 3Step TTS 2 (Mar 2026)ClosedStepFun1,148±14
16▼ 3Speech 2.6 TurboClosedMiniMax1,142±12
17▼ 1Speech 2.6 HDClosedMiniMax1,136±12
18▼ 3SIMBA 3.0ClosedSpeechify1,132±14
19▼ 2Fish Audio S2 ProOpenFish Audio1,122±14
20▼ 2Azure HD 2.5ClosedMicrosoft1,121±14
21▼ 2Inworld TTS 1ClosedInworld1,120±13
22▼ 1Step Audio EditX (Mar 2026)OpenStepFun1,112±15
23▼ 3Speech-02-HDClosedMiniMax1,110±12
24▼ 1Turbo v2.5ClosedElevenLabs1,105±11
25▼ 3Multilingual v2ClosedElevenLabs1,103±11
26▼ 2Gradium TTSClosedGradium1,099±16
27▼ 2Flash v2.5ClosedElevenLabs1,099±11
28▲ 2Lightning V3.1 ProClosedSmallest.ai1,091±15
29▼ 1TTS-1ClosedOpenAI1,090±11
30▼ 3Speech-02-TurboClosedMiniMax1,090±12
31▲ 24Chatterbox HDClosedResemble AI1,088±14
32▼ 6TTS-1 HDClosedOpenAI1,086±12
33▼ 1Gemini 2.5 Flash Lite TTSClosedGoogle1,085±13
34▼ 5Sonic 3ClosedCartesia1,082±12
35▼ 2StudioClosedGoogle1,080±12
36▼ 1Voxtral TTSOpenMistral1,080±15
37▼ 6MiMo-V2.5-TTSClosedXiaomi1,078±15
38▼ 4Polly GenerativeClosedAmazon1,069±12
39▼ 1Azure NeuralClosedMicrosoft1,067±12
40—T2A-01-HDClosedMiniMax1,063±11
41▲ 1OpenAudio S1ClosedFish Audio1,062±11
42▼ 6Polly Long-FormClosedAmazon1,060±14
43▼ 4Kokoro 82M v1.0OpenKokoro1,059±11
44▼ 3Async Flash v1.0ClosedAsync1,059±12
45—Octave 2ClosedHume AI1,058±12
46▼ 3Chirp 3: HDClosedGoogle1,055±12
47▼ 3Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant1,054±15
48▼ 11SIMBA 1.6ClosedSpeechify1,051±14
49▼ 3Sonic English (Oct 2024)ClosedCartesia1,050±12
50▲ 1Gemini 2.5 Pro (Dec 2025)ClosedGoogle1,043±15

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.