Skip to content
IFAI

Model rankings

1283 models · 5 boards · 2 sources

‹
Week of June 22, 2026
August 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 changesMay 18, 202616 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated June 28, 2026

Best voice
Sonic 3.5Cartesia1,218Score
Best open model
Step Audio EditX (Mar 2026)StepFun1,113Score
Best from China
Fun-Realtime-TTSAlibaba1,210Score
Top three by Score
1Sonic 3.5Cartesia1,218
2Gemini 3.1 Flash TTSGoogle1,216
3Fun-Realtime-TTSAlibaba1,210
Top three open models
1Step Audio EditX (Mar 2026)StepFun · #21 overall1,113
2Fish Audio S2 ProFish Audio · #23 overall1,111
3Voxtral TTSMistral · #36 overall1,075
This week's changes
MAI-Image-2.5Image · #2New
MAI-Image-2.5-FlashImage · #9New
Luna TTSSpeech · #9New
Nex-N2-ProIntelligence · #20New
Grok Build 0.1 0616Intelligence · #29New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1▲ 3Sonic 3.5ClosedCartesia1,218±14
2—Gemini 3.1 Flash TTSClosedGoogle1,216±13
3▼ 2Fun-Realtime-TTSClosedAlibaba1,210±14
4▼ 1Realtime TTS-2 - Research PreviewClosedInworld1,202±14
5—xAI Text to SpeechClosedxAI1,197±14
6—Realtime TTS 1.5 MaxClosedInworld1,197±14
7—Async Flash v1.5ClosedAsync1,186±15
8—StepAudio 2.5 TTSClosedStepFun1,184±17
9NewLuna TTSClosedVUI Labs1,181±16
10▼ 1Eleven v3ClosedElevenLabs1,179±12
11▼ 1Speech 2.8 HDClosedMiniMax1,171±12
12▼ 1Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai1,167±15
13▼ 1Async Pro v1.0ClosedAsync1,157±15
14—Speech 2.8 TurboClosedMiniMax1,152±12
15▼ 2Step TTS 2 (Mar 2026)ClosedStepFun1,150±14
16▼ 1Realtime TTS 1.5 MiniClosedInworld1,150±13
17▼ 1Speech 2.6 TurboClosedMiniMax1,137±12
18—SIMBA 3.0ClosedSpeechify1,134±14
19▼ 2Speech 2.6 HDClosedMiniMax1,132±12
20▼ 1Azure HD 2.5ClosedMicrosoft1,120±14
21▲ 1Step Audio EditX (Mar 2026)OpenStepFun1,113±14
22▼ 1Multilingual v2ClosedElevenLabs1,111±10
23▼ 3Fish Audio S2 ProOpenFish Audio1,111±14
24—Speech-02-HDClosedMiniMax1,109±12
25▼ 2Turbo v2.5ClosedElevenLabs1,108±11
26▼ 1Gradium TTSClosedGradium1,104±15
27—TTS-1 HDClosedOpenAI1,097±12
28▼ 2Flash v2.5ClosedElevenLabs1,095±11
29▲ 16Gradium TTS (Jun 2026)ClosedGradium1,095±16
30▼ 2Speech-02-TurboClosedMiniMax1,089±12
31▲ 4MiMo-V2.5-TTSClosedXiaomi1,089±14
32▼ 1Chatterbox HDClosedResemble AI1,087±13
33▼ 4TTS-1ClosedOpenAI1,086±11
34▼ 4Sonic 3ClosedCartesia1,082±12
35▼ 3Gemini 2.5 Flash Lite TTSClosedGoogle1,079±12
36▼ 3StudioClosedGoogle1,076±12
37▼ 3Voxtral TTSOpenMistral1,075±14
38▼ 2Polly GenerativeClosedAmazon1,072±12
39NewGPT-Realtime-2ClosedOpenAI1,070±15
40▲ 4SIMBA 1.6ClosedSpeechify1,068±13
41▼ 3OpenAudio S1ClosedFish Audio1,066±11
42▼ 1Polly Long-FormClosedAmazon1,066±14
43▼ 1Kokoro 82M v1.0OpenKokoro1,063±11
44▼ 5T2A-01-HDClosedMiniMax1,062±11
45▼ 5Octave 2ClosedHume AI1,061±12
46▲ 1Chirp 3: HDClosedGoogle1,057±12
47▼ 1Async Flash v1.0ClosedAsync1,057±12
48—JourneyClosedGoogle1,057±13
49▼ 6Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA1,056±14
50▼ 1Maya1OpenMaya Research1,054±12

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 “—”.