Skip to content
IFAI

Model rankings

1319 models · 5 boards · 2 sources

‹
Week of June 29, 2026
August 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 changesMay 25, 202617 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated July 5, 2026

Best voice
Gemini 3.1 Flash TTSGoogle1,215Score
Best open model
Step Audio EditX (Mar 2026)StepFun1,114Score
Best from China
Fun-Realtime-TTSAlibaba1,206Score
Top three by Score
1Gemini 3.1 Flash TTSGoogle1,215
2Sonic 3.5Cartesia1,209
3Fun-Realtime-TTSAlibaba1,206
Top three open models
1Step Audio EditX (Mar 2026)StepFun · #22 overall1,114
2Fish Audio S2 ProFish Audio · #23 overall1,110
3Voxtral TTSMistral · #34 overall1,076
This week's changes
Reve 2.0Image · #2New
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Intelligence · #5New
claude-sonnet-5-thinkingCoding · #5New
Fish Audio S2.1 ProSpeech · #15New
OpenAudio S1 MiniSpeech · #50New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1▲ 1Gemini 3.1 Flash TTSClosedGoogle1,215±14
2▼ 1Sonic 3.5ClosedCartesia1,209±15
3—Fun-Realtime-TTSClosedAlibaba1,206±15
4—Realtime TTS-2 - Research PreviewClosedInworld1,201±15
5▲ 1Realtime TTS 1.5 MaxClosedInworld1,199±15
6▼ 1xAI Text to SpeechClosedxAI1,188±15
7▲ 4Speech 2.8 HDClosedMiniMax1,184±13
8▼ 1Async Flash v1.5ClosedAsync1,180±16
9—Luna TTSClosedVUI Labs1,175±17
10▼ 2StepAudio 2.5 TTSClosedStepFun1,174±18
11▼ 1Eleven v3ClosedElevenLabs1,172±13
12▲ 1Async Pro v1.0ClosedAsync1,155±16
13▼ 1Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai1,150±16
14—Speech 2.8 TurboClosedMiniMax1,149±13
15NewFish Audio S2.1 ProClosedFish Audio1,146±16
16—Realtime TTS 1.5 MiniClosedInworld1,144±13
17▼ 2Step TTS 2 (Mar 2026)ClosedStepFun1,142±15
18▲ 1Speech 2.6 HDClosedMiniMax1,141±13
19▼ 2Speech 2.6 TurboClosedMiniMax1,136±12
20—Azure HD 2.5ClosedMicrosoft1,125±14
21▼ 3SIMBA 3.0ClosedSpeechify1,124±14
22▼ 1Step Audio EditX (Mar 2026)OpenStepFun1,114±15
23—Fish Audio S2 ProOpenFish Audio1,110±15
24▼ 2Multilingual v2ClosedElevenLabs1,108±11
25—Turbo v2.5ClosedElevenLabs1,106±11
26▼ 2Speech-02-HDClosedMiniMax1,105±12
27—TTS-1 HDClosedOpenAI1,100±13
28▼ 2Gradium TTSClosedGradium · 1 more variant1,094±16
29—Speech-02-TurboClosedMiniMax1,093±13
30▼ 2Flash v2.5ClosedElevenLabs1,091±11
31—Chatterbox HDClosedResemble AI1,089±14
32—TTS-1ClosedOpenAI1,083±11
33▼ 3MiMo-V2.5-TTSClosedXiaomi1,077±15
34▲ 2Voxtral TTSOpenMistral1,076±15
35▼ 2Sonic 3ClosedCartesia1,073±13
36▼ 2Gemini 2.5 Flash Lite TTSClosedGoogle1,072±13
37—Polly GenerativeClosedAmazon1,069±12
38▼ 3StudioClosedGoogle1,069±12
39▼ 1GPT-Realtime-2ClosedOpenAI1,068±16
40—OpenAudio S1ClosedFish Audio1,065±12
41▼ 2SIMBA 1.6ClosedSpeechify1,063±14
42▲ 1T2A-01-HDClosedMiniMax1,061±12
43▲ 1Octave 2ClosedHume AI1,060±13
44▼ 2Kokoro 82M v1.0OpenKokoro1,059±11
45▼ 4Polly Long-FormClosedAmazon1,056±14
46—Async Flash v1.0ClosedAsync1,051±12
47▲ 2Maya1OpenMaya Research1,051±13
48▼ 3Chirp 3: HDClosedGoogle1,050±13
49▼ 1Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant1,047±15
50NewOpenAudio S1 MiniClosedFish Audio1,044±19

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 “—”.