Skip to content
IFAI

Model rankings

1396 models · 5 boards · 2 sources

‹
Week of August 3, 2026
September 14, 2026174 changesSeptember 7, 2026144 changesAugust 31, 202620 changesAugust 24, 202615 changesAugust 17, 202633 changesAugust 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated July 13, 2026

Best voice
Simba 3.2SpeechifyAI1,234Score
Best open model
Step Audio EditX (Mar 2026)StepFun1,118Score
Best from China
Fun-Realtime-TTSAlibaba1,205Score
Top three by Score
1Simba 3.2SpeechifyAI1,234
2Gemini 3.1 Flash TTSGoogle1,214
3Sonic 3.5Cartesia1,207
Top three open models
1Step Audio EditX (Mar 2026)StepFun · #23 overall1,118
2Fish Audio S2 ProFish Audio · #24 overall1,110
3Voxtral TTSMistral · #34 overall1,077
This week's changes
muse-spark-1.2 (xHigh)Coding · #13New
gemini-3.5-flash-highCoding · #25New
Inkling SmallIntelligence · #36New
Celeris-1Intelligence · #221New
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)Intelligence · #17Up 18
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1—Simba 3.2ClosedSpeechifyAI1,234±17
2—Gemini 3.1 Flash TTSClosedGoogle1,214±14
3—Sonic 3.5ClosedCartesia1,207±14
4—Fun-Realtime-TTSClosedAlibaba1,205±15
5—Realtime TTS-2 - Research PreviewClosedInworld1,205±15
6—Realtime TTS 1.5 MaxClosedInworld1,204±15
7—SpaceXAI TTSClosedSpaceXAI1,189±15
8—Speech 2.8 HDClosedMiniMax1,185±13
9—Async Flash v1.5ClosedAsync1,182±16
10—Luna TTSClosedVUI Labs1,176±17
11—StepAudio 2.5 TTSClosedStepFun1,175±18
12—Eleven v3ClosedElevenLabs1,174±13
13—Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai1,152±16
14—Speech 2.8 TurboClosedMiniMax1,149±12
15—Async Pro v1.0ClosedAsync1,147±16
16—Step TTS 2 (Mar 2026)ClosedStepFun1,144±15
17—Realtime TTS 1.5 MiniClosedInworld1,142±13
18—Fish Audio S2.1 ProClosedFish Audio1,142±16
19—Speech 2.6 HDClosedMiniMax1,141±13
20—Speech 2.6 TurboClosedMiniMax1,134±12
21—Azure HD 2.5ClosedMicrosoft1,124±14
22—Simba 3.0ClosedSpeechifyAI1,122±14
23—Step Audio EditX (Mar 2026)OpenStepFun1,118±15
24—Fish Audio S2 ProOpenFish Audio1,110±15
25—Multilingual v2ClosedElevenLabs1,107±11
26—Turbo v2.5ClosedElevenLabs1,106±11
27—Speech-02-HDClosedMiniMax1,106±12
28—TTS-1 HDClosedOpenAI1,100±13
29—Flash v2.5ClosedElevenLabs1,093±11
30—Speech-02-TurboClosedMiniMax1,089±12
31—Gradium TTSClosedGradium1,088±16
32—Chatterbox HDClosedResemble AI1,088±14
33—TTS-1ClosedOpenAI1,084±11
34—Voxtral TTSOpenMistral1,077±15
35—MiMo-V2.5-TTSClosedXiaomi1,077±15
36—Gemini 2.5 Flash Lite TTSClosedGoogle1,073±13
37—Sonic 3ClosedCartesia1,073±12
38—GPT-Realtime-2ClosedOpenAI1,069±16
39—StudioClosedGoogle1,069±12
40—Polly GenerativeClosedAmazon1,068±12
41—OpenAudio S1ClosedFish Audio1,067±12
42—SIMBA 1.6ClosedSpeechifyAI1,064±14
43—T2A-01-HDClosedMiniMax1,062±12
44—Kokoro 82M v1.0OpenKokoro1,060±11
45—Octave 2ClosedHume AI1,058±13
46—Maya1OpenMaya Research1,053±13
47—Async Flash v1.0ClosedAsync1,052±12
48—Polly Long-FormClosedAmazon1,051±14
49—Chirp 3: HDClosedGoogle1,050±13
50—Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA1,048±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 “—”.