AI Model Leaderboards
AI Speech Synthesis Elo Ranking
Speech synthesis models ranked by Artificial Analysis's text-to-speech arena Elo: a relative score from head-to-head battles, comparable only within this board. Synced once a day.
1,316ElevenLabs: Eleven v4Eleven v495% CI ±18
1,275Cartesia: Sonic 3.6Sonic 3.695% CI ±16
1,268- 4
1,258Qwen: Qwen-Audio-3.0-TTS-PlusQwen-Audio-3.0-TTS-Plus95% CI ±16
- 5
1,247Inworld: Realtime TTS-2Realtime TTS-295% CI ±17
- 6
1,241SpeechifyAI: Simba 3.2Simba 3.295% CI ±14
- 71,240
- 8V1,230VUI Labs: Luna TTSLuna TTS
95% CI ±13
- 91,210Inworld: Realtime TTS-2 FlashRealtime TTS-2 Flash
95% CI ±15
- 10B1,207BreezeBlue: Breeze TTS 2Breeze TTS 2
95% CI ±16
- 11
1,206StepFun: StepAudio 2.5 TTSStepAudio 2.5 TTS95% CI ±16
- 121,204
- 131,199ElevenLabs: v3 Conversationalv3 Conversational
95% CI ±15
- 141,187Cartesia: Sonic 3.5Sonic 3.5
95% CI ±12
- 15
1,175Soniox: Soniox TTS Real-Time v2Soniox TTS Real-Time v295% CI ±12
- 16
1,171MiniMax: Speech 2.8 HDSpeech 2.8 HD95% CI ±11
- 171,170ElevenLabs: Eleven v3Eleven v3
95% CI ±11
- 18
1,168Smallest.ai: Lightning V3.1 ProLightning V3.1 Pro95% CI ±14
- 19
1,154Murf AI: Falcon 2Falcon 295% CI ±14
- 201,150MiniMax: Speech 2.8 TurboSpeech 2.8 Turbo
95% CI ±11
- 21
1,149Gradium: Gradium TTSGradium TTS95% CI ±14
- 22
1,139Fish Audio: Fish Audio S2.1 ProFish Audio S2.1 Pro95% CI ±13
- 23A1,134async: Async Flash v1.5Async Flash v1.5
95% CI ±13
- 241,134StepFun: Step TTS 2Step TTS 2
95% CI ±13
- 25
1,13395% CI ±15
- 26
1,128Microsoft: Azure HD 2.5Azure HD 2.595% CI ±12
- 271,128MiniMax: Speech 2.6 HDSpeech 2.6 HD
95% CI ±11
- 281,122SpeechifyAI: Simba 3.0Simba 3.0
95% CI ±12
- 291,119MiniMax: Speech 2.6 TurboSpeech 2.6 Turbo
95% CI ±11
- 301,118Fish Audio: Fish Audio S2 ProFish Audio S2 Pro
95% CI ±12
- 31A1,117async: Async Pro v1.0Async Pro v1.0
95% CI ±13
- 321,112MiniMax: Speech-02-HDSpeech-02-HD
95% CI ±11
- 33
1,102Resemble AI: Chatterbox HDChatterbox HD95% CI ±13
- 34
1,10295% CI ±12
- 35
1,099Hithink: Speech 2.6Speech 2.695% CI ±13
- 361,095ElevenLabs: Turbo v2.5Turbo v2.5
95% CI ±11
- 371,093ElevenLabs: Multilingual v2Multilingual v2
95% CI ±10
- 381,093StepFun: Step Audio EditXStep Audio EditX
95% CI ±13
- 391,089
95% CI ±11
- 401,088MiniMax: Speech-02-TurboSpeech-02-Turbo
95% CI ±12
- 411,081
- 421,080Fish Audio: OpenAudio S1OpenAudio S1
95% CI ±11
- 43
1,080Mistral: Voxtral TTSVoxtral TTS95% CI ±13
- 441,077
95% CI ±13
- 451,076ElevenLabs: Flash v2.5Flash v2.5
95% CI ±11
- 461,076
95% CI ±12
- 471,074
95% CI ±13
- 48M1,074Maya Research: Maya 2 FlashMaya 2 Flash
95% CI ±14
- 49K1,064Kokoro: Kokoro 82M v1.0Kokoro 82M v1.0
95% CI ±11
- 50
1,064Amazon: Polly GenerativePolly Generative95% CI ±12
Source: Artificial Analysis · arena Elo rating, as of Sep 30, 2026. Elo comes from head-to-head arena battles rather than a fixed exam, so it is a relative score: it only compares within the same board, and it gets steadier as more battles come in.
Arena ratings come from Artificial Analysis's public evaluations and sync once a day; scores for brand-new models move around more until enough battles are in. Names link to the matching tool page on our site.
Disclaimer: this board is generated automatically from third-party public data, for reference only, with no warranty or recommendation and no view on any product's safety or legality; names and trademarks belong to their respective owners, and we are not affiliated with or endorsed by these products. To report an error or ask for a correction or removal, use the contact details on our cooperation page to reach us. By using this site you accept our Terms of Service and Privacy Policy, and we accept no liability for any loss arising from use of this board.