Skip to content
IFAI

Model rankings

1356 models · 5 boards · 2 sources

‹
Week of July 6, 2026
August 17, 202633 changesAugust 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated July 10, 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
gpt-5.6-sol-xhigh (codex-harness)Coding · #1New
Simba 3.2Speech · #1New
GPT-5.6 Sol (max)Intelligence · #2New
GPT-5.6 Terra (max)Intelligence · #4New
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Image · #5New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1NewSimba 3.2ClosedSpeechifyAI1,234±17
2▼ 1Gemini 3.1 Flash TTSClosedGoogle1,214±14
3▼ 1Sonic 3.5ClosedCartesia1,207±14
4▼ 1Fun-Realtime-TTSClosedAlibaba1,205±15
5▼ 1Realtime TTS-2 - Research PreviewClosedInworld1,205±15
6▼ 1Realtime TTS 1.5 MaxClosedInworld1,204±15
7NewSpaceXAI TTSClosedSpaceXAI1,189±15
8▼ 1Speech 2.8 HDClosedMiniMax1,185±13
9▼ 1Async Flash v1.5ClosedAsync1,182±16
10▼ 1Luna TTSClosedVUI Labs1,176±17
11▼ 1StepAudio 2.5 TTSClosedStepFun1,175±18
12▼ 1Eleven v3ClosedElevenLabs1,174±13
13—Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai1,152±16
14—Speech 2.8 TurboClosedMiniMax1,149±12
15▼ 3Async Pro v1.0ClosedAsync1,147±16
16▲ 1Step TTS 2 (Mar 2026)ClosedStepFun1,144±15
17▼ 1Realtime TTS 1.5 MiniClosedInworld1,142±13
18▼ 3Fish Audio S2.1 ProClosedFish Audio1,142±16
19▼ 1Speech 2.6 HDClosedMiniMax1,141±13
20▼ 1Speech 2.6 TurboClosedMiniMax1,134±12
21▼ 1Azure HD 2.5ClosedMicrosoft1,124±14
22NewSimba 3.0ClosedSpeechifyAI1,122±14
23▼ 1Step Audio EditX (Mar 2026)OpenStepFun1,118±15
24▼ 1Fish Audio S2 ProOpenFish Audio1,110±15
25▼ 1Multilingual v2ClosedElevenLabs1,107±11
26▼ 1Turbo v2.5ClosedElevenLabs1,106±11
27▼ 1Speech-02-HDClosedMiniMax1,106±12
28▼ 1TTS-1 HDClosedOpenAI1,100±13
29▲ 1Flash v2.5ClosedElevenLabs1,093±11
30▼ 1Speech-02-TurboClosedMiniMax1,089±12
31▼ 3Gradium TTSClosedGradium1,088±16
32▼ 1Chatterbox HDClosedResemble AI1,088±14
33—TTS-1ClosedOpenAI1,084±11
34▲ 1Voxtral TTSOpenMistral1,077±15
35▼ 1MiMo-V2.5-TTSClosedXiaomi1,077±15
36▲ 1Gemini 2.5 Flash Lite TTSClosedGoogle1,073±13
37▼ 1Sonic 3ClosedCartesia1,073±12
38▲ 2GPT-Realtime-2ClosedOpenAI1,069±16
39—StudioClosedGoogle1,069±12
40▼ 2Polly GenerativeClosedAmazon1,068±12
41—OpenAudio S1ClosedFish Audio1,067±12
42—SIMBA 1.6ClosedSpeechifyAI1,064±14
43—T2A-01-HDClosedMiniMax1,062±12
44▲ 1Kokoro 82M v1.0OpenKokoro1,060±11
45▼ 1Octave 2ClosedHume AI1,058±13
46▲ 2Maya1OpenMaya Research1,053±13
47—Async Flash v1.0ClosedAsync1,052±12
48▼ 2Polly 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 “—”.