Skip to content
IFAI

Model rankings

1447 models · 5 boards · 2 sources

‹
Week of August 24, 2026
October 5, 202634 changesSeptember 28, 202617 changesSeptember 21, 2026115 changesSeptember 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 changes
›

Text-to-speech arena · Anonymous head-to-head votes · Updated August 18, 2026

Best voice
Sonic 3.6Cartesia1,283Score
Best open model
Fish Audio S2 ProFish Audio1,126Score
Best from China
Qwen-Audio-3.0-TTS-PlusAlibaba1,240Score
Top three by Score
1Sonic 3.6Cartesia1,283
2Qwen-Audio-3.0-TTS-PlusAlibaba1,240
3Simba 3.2SpeechifyAI1,240
Top three open models
1Fish Audio S2 ProFish Audio · #25 overall1,126
2Step Audio EditX (Mar 2026)StepFun · #30 overall1,107
3Voxtral TTSMistral · #40 overall1,079
This week's changes
hy4-previewCoding · #5New
GLM-5.3 (max)Intelligence · #6New
MAI-Image-2.5-ProImage · #7New
qwen3.8-flash-nextCoding · #8New
glm-5.3-flashCoding · #11New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1—Sonic 3.6ClosedCartesia1,283±17
2—Qwen-Audio-3.0-TTS-PlusClosedAlibaba1,240±14
3—Simba 3.2ClosedSpeechifyAI1,240±14
4—Luna TTSClosedVUI Labs1,219±14
5—Gemini 3.1 Flash TTSClosedGoogle1,211±12
6—StepAudio 2.5 TTSClosedStepFun1,206±14
7—Sonic 3.5ClosedCartesia1,204±13
8—Realtime TTS 1.5 MaxClosedInworld1,195±13
9—Lightning V3.1 Pro (Jul 2026)ClosedSmallest.ai1,193±15
10—Realtime TTS-2 - Research PreviewClosedInworld1,188±13
11—Eleven v3ClosedElevenLabs1,179±11
12—Speech 2.8 HDClosedMiniMax1,174±11
13—Falcon 2ClosedMurf AI1,155±15
14—Speech 2.8 TurboClosedMiniMax1,154±11
15—Gradium TTS BetaClosedGradium1,151±15
16—Async Flash v1.5ClosedAsync1,150±13
17—Fish Audio S2.1 ProClosedFish Audio1,144±13
18—Step TTS 2 (Mar 2026)ClosedStepFun1,141±13
19—Speech 2.6 HDClosedMiniMax1,136±11
20—Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai1,136±13
21—Realtime TTS 1.5 MiniClosedInworld1,132±12
22—Azure HD 2.5ClosedMicrosoft1,132±12
23—Async Pro v1.0ClosedAsync1,129±13
24—Speech 2.6 TurboClosedMiniMax1,127±11
25—Fish Audio S2 ProOpenFish Audio1,126±13
26—Simba 3.0ClosedSpeechifyAI1,124±12
27—SpaceXAI TTSClosedSpaceXAI1,118±16
28—Speech-02-HDClosedMiniMax1,111±11
29—TTS-1 HDClosedOpenAI1,107±12
30—Step Audio EditX (Mar 2026)OpenStepFun1,107±13
31—Turbo v2.5ClosedElevenLabs1,104±10
32—Multilingual v2ClosedElevenLabs1,104±10
33—Chatterbox HDClosedResemble AI1,095±13
34—TTS-1ClosedOpenAI1,094±11
35—Gradium TTSClosedGradium1,093±13
36—Gemini 2.5 Flash Lite TTSClosedGoogle1,089±12
37—Speech-02-TurboClosedMiniMax1,085±11
38—Flash v2.5ClosedElevenLabs1,084±11
39—StudioClosedGoogle1,081±11
40—Voxtral TTSOpenMistral1,079±13
41—Speech 2.6ClosedHithink1,077±13
42—OpenAudio S1ClosedFish Audio1,076±11
43—GPT-Realtime-2ClosedOpenAI1,072±13
44—Sonic 3ClosedCartesia1,072±11
45—Bland Speech v3ClosedBland AI1,071±12
46—Maya 2 FlashClosedMaya Research1,070±14
47—JourneyClosedGoogle1,069±13
48—T2A-01-HDClosedMiniMax1,065±11
49—Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant1,065±13
50—SIMBA 1.6ClosedSpeechifyAI1,065±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 “—”.