Skip to content
IFAI

Model rankings

1432 models · 5 boards · 2 sources

‹
Week of August 17, 2026
September 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 changesJuly 13, 202611 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
Sonic 3.6Speech · #1New
Grok 4.6 (high)Intelligence · #4New
Qwen3.8 2.4T A95BIntelligence · #7New
glm-5.3-maxCoding · #8New
Qwen-Image-3.0-ProImage · #8New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
RankChangeModelScore95% interval
1NewSonic 3.6ClosedCartesia1,283±17
2—Qwen-Audio-3.0-TTS-PlusClosedAlibaba1,240±14
3▼ 2Simba 3.2ClosedSpeechifyAI1,240±14
4▼ 1Luna TTSClosedVUI Labs1,219±14
5▼ 1Gemini 3.1 Flash TTSClosedGoogle1,211±12
6▼ 1StepAudio 2.5 TTSClosedStepFun1,206±14
7▼ 1Sonic 3.5ClosedCartesia1,204±13
8▼ 1Realtime TTS 1.5 MaxClosedInworld1,195±13
9▼ 1Lightning V3.1 Pro (Jul 2026)ClosedSmallest.ai1,193±15
10▼ 1Realtime TTS-2 - Research PreviewClosedInworld1,188±13
11—Eleven v3ClosedElevenLabs1,179±11
12▼ 2Speech 2.8 HDClosedMiniMax1,174±11
13▲ 1Falcon 2ClosedMurf AI1,155±15
14▼ 1Speech 2.8 TurboClosedMiniMax1,154±11
15▼ 3Gradium TTS BetaClosedGradium1,151±15
16▼ 1Async Flash v1.5ClosedAsync1,150±13
17▼ 1Fish Audio S2.1 ProClosedFish Audio1,144±13
18▼ 1Step TTS 2 (Mar 2026)ClosedStepFun1,141±13
19—Speech 2.6 HDClosedMiniMax1,136±11
20▼ 2Lightning V3.1 Pro TTS (Jun 2026)ClosedSmallest.ai1,136±13
21▼ 1Realtime TTS 1.5 MiniClosedInworld1,132±12
22▼ 1Azure HD 2.5ClosedMicrosoft1,132±12
23▼ 1Async Pro v1.0ClosedAsync1,129±13
24—Speech 2.6 TurboClosedMiniMax1,127±11
25▼ 2Fish Audio S2 ProOpenFish Audio1,126±13
26▼ 1Simba 3.0ClosedSpeechifyAI1,124±12
27▲ 1SpaceXAI TTSClosedSpaceXAI1,118±16
28▼ 2Speech-02-HDClosedMiniMax1,111±11
29—TTS-1 HDClosedOpenAI1,107±12
30▼ 3Step Audio EditX (Mar 2026)OpenStepFun1,107±13
31—Turbo v2.5ClosedElevenLabs1,104±10
32▼ 2Multilingual v2ClosedElevenLabs1,104±10
33▼ 1Chatterbox HDClosedResemble AI1,095±13
34▼ 1TTS-1ClosedOpenAI1,094±11
35▼ 1Gradium TTSClosedGradium1,093±13
36▲ 1Gemini 2.5 Flash Lite TTSClosedGoogle1,089±12
37▼ 1Speech-02-TurboClosedMiniMax1,085±11
38▼ 3Flash v2.5ClosedElevenLabs1,084±11
39▼ 1StudioClosedGoogle1,081±11
40▲ 2Voxtral TTSOpenMistral1,079±13
41▼ 1Speech 2.6ClosedHithink1,077±13
42▼ 1OpenAudio S1ClosedFish Audio1,076±11
43▲ 5GPT-Realtime-2ClosedOpenAI1,072±13
44▼ 1Sonic 3ClosedCartesia1,072±11
45NewBland Speech v3ClosedBland AI1,071±12
46▼ 7Maya 2 FlashClosedMaya Research1,070±14
47▼ 1JourneyClosedGoogle1,069±13
48▲ 1T2A-01-HDClosedMiniMax1,065±11
49▼ 5Magpie-Multilingual 357M (Feb 2026)OpenNVIDIA · 1 more variant1,065±13
50▼ 3SIMBA 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 “—”.