Skip to content
IFAI

Model rankings

1203 models · 5 boards · 2 sources

‹
Week of May 4, 2026
June 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changesMay 18, 202616 changesMay 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changesApril 20, 202627 changesApril 13, 202637 changesApril 6, 202641 changesMarch 30, 2026230 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated May 10, 2026

Best voice
Realtime TTS 1.5 MaxInworld1,208Score
Best open model
Fish Audio S2 ProFish Audio1,128Score
Best from China
StepAudio 2.5 TTSStepFun1,187Score
Top three by Score
1Realtime TTS 1.5 MaxInworld1,208
2Gemini 3.1 Flash TTSGoogle1,206
3StepAudio 2.5 TTSStepFun1,187
Top three open models
1Fish Audio S2 ProFish Audio · #13 overall1,128
2Step Audio EditX (Mar 2026)StepFun · #18 overall1,104
3Magpie-Multilingual 357M (Feb 2026)NVIDIA · #28 overall1,063
This week's changes
StepAudio 2.5 TTSSpeech · #3New
Bach-1.0 PreviewVideo · #7New
SIMBA 3.0Speech · #7New
qwen3.6-max-previewCoding · #9New
Peanut (Open Weights Coming Soon)Image · #9New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1—Realtime TTS 1.5 MaxClosedInworld1,208±18
2—Gemini 3.1 Flash TTSClosedGoogle1,206±17
3NewStepAudio 2.5 TTSClosedStepFun1,187±26
4▼ 1Eleven v3ClosedElevenLabs1,178±12
5▼ 1Inworld TTS 1 MaxClosedInworld1,164±17
6▼ 1Speech 2.8 HDClosedMiniMax1,163±12
7NewSIMBA 3.0ClosedSpeechify1,159±36
8▼ 2Realtime TTS 1.5 MiniClosedInworld1,158±15
9▼ 2Step TTS 2 (Mar 2026)ClosedStepFun1,148±19
10▼ 2Speech 2.8 TurboClosedMiniMax1,146±11
11▼ 2Speech 2.6 HDClosedMiniMax1,133±12
12▼ 2Speech 2.6 TurboClosedMiniMax1,129±11
13▼ 2Fish Audio S2 ProOpenFish Audio1,128±21
14▼ 2Azure HD 2.5ClosedMicrosoft1,120±21
15▼ 2Speech-02-HDClosedMiniMax1,117±11
16▼ 2Inworld TTS 1ClosedInworld1,116±16
17▼ 2Multilingual v2ClosedElevenLabs1,107±8
18▼ 2Step Audio EditX (Mar 2026)OpenStepFun1,104±21
19▼ 2TTS-1ClosedOpenAI1,101±8
20▼ 1Turbo v2.5ClosedElevenLabs1,098±8
21▼ 1TTS-1 HDClosedOpenAI1,097±12
22▼ 4Speech-02-TurboClosedMiniMax1,096±11
23NewMiMo-V2.5-TTSClosedXiaomi1,089±36
24▼ 3Flash v2.5ClosedElevenLabs1,087±9
25▼ 2Gemini 2.5 Flash Lite TTSClosedGoogle1,080±14
26▼ 2Sonic 3ClosedCartesia1,069±13
27▼ 5Gradium TTSClosedGradium1,066±33
28▼ 2Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant1,063±21
29▼ 4OpenAudio S1ClosedFish Audio1,063±10
30▼ 2StudioClosedGoogle1,062±10
31▼ 4SIMBA 1.6ClosedSpeechify1,060±19
32▼ 3T2A-01-HDClosedMiniMax1,057±10
33▼ 2Polly GenerativeClosedAmazon1,056±11
34▼ 4Kokoro 82M v1.0OpenKokoro1,056±9
35▼ 3Voxtral TTSOpenMistral1,056±21
36▼ 3AsyncFlow V2, asyncClosedAsync1,052±11
37▼ 3Maya1OpenMaya Research1,050±13
38▼ 3Azure NeuralClosedMicrosoft1,048±8
39▼ 3Sonic English (Oct 2024)ClosedCartesia1,047±12
40—Polly Long-FormClosedAmazon1,044±19
41▼ 4Octave 2ClosedHume AI1,042±13
42▼ 4Chirp 3: HDClosedGoogle1,040±12
43▼ 2Chatterbox HDClosedResemble AI1,035±10
44▼ 2JourneyClosedGoogle1,033±18
45▼ 6Lightning v3.1ClosedSmallest.ai1,033±20
46▼ 3Gemini 2.5 Flash TTS (Dec 2025)ClosedGoogle1,029±15
47▼ 3SIMBA 1.0ClosedSpeechify1,026±10
48▼ 1MAI-Voice-1ClosedMicrosoft1,023±20
49▼ 4Gemini 2.5 Pro (Dec 2025)ClosedGoogle1,023±16
50▼ 2Octave TTSClosedHume AI1,018±10

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 “—”.