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.
1,340ElevenLabs: Eleven v4Eleven v495% CI ±15
1,340ElevenLabs: Eleven v4 TurboEleven v4 Turbo95% CI ±15
1,298Qwen: Qwen-Audio-3.1-TTS-PlusQwen-Audio-3.1-TTS-Plus95% CI ±14
- 4
1,295Cartesia: Sonic 3.6Sonic 3.695% CI ±13
- 5
1,291SpeechifyAI: Simba 3.5Simba 3.595% CI ±17
- 6
1,283 - 7
1,277Fish Audio: Fish Audio Drama 3Fish Audio Drama 395% CI ±17
- 8
1,273Smallest.ai: Lightning V3.1 ProLightning V3.1 Pro95% CI ±15
- 9
1,268Inworld: Realtime TTS-2Realtime TTS-295% CI ±13
- 10
1,265Qwen: Qwen-Audio-3.0-TTS-PlusQwen-Audio-3.0-TTS-Plus95% CI ±13
- 11
1,259 - 12
1,251SpeechifyAI: Simba 3.2Simba 3.295% CI ±11
- 13
1,238Fish Audio: Fish Audio Drama 3 PreviewFish Audio Drama 3 Preview95% CI ±13
- 14B1,229BreezeBlue: Breeze TTS 2Breeze TTS 2
95% CI ±12
- 15
1,216ElevenLabs: v3 Conversationalv3 Conversational95% CI ±12
- 16A1,215AssemblyAI: AssemblyAI-TTS-1AssemblyAI-TTS-1
95% CI ±15
- 17
1,215StepFun: StepAudio 2.5 TTSStepAudio 2.5 TTS95% CI ±12
- 18
1,214Inworld: Realtime TTS-2 FlashRealtime TTS-2 Flash95% CI ±12
- 19
1,213 - 20
1,212Mistral: Voxtral 3 TTSVoxtral 3 TTS95% CI ±13
- 21V1,197VUI Labs: Luna TTSLuna TTS
95% CI ±11
- 22
1,196Cartesia: Sonic 3.5Sonic 3.595% CI ±11
- 23
1,190ElevenLabs: Eleven v3Eleven v395% CI ±10
- 24
1,184Fish Audio: Fish Audio S2.1 ProFish Audio S2.1 Pro95% CI ±13
- 25A1,183Ant Group: Ming-3.0-ttsMing-3.0-tts
95% CI ±13
- 26
1,182Soniox: Soniox TTS Real-Time v2Soniox TTS Real-Time v295% CI ±10
- 27
1,176Gradium: Gradium TTSGradium TTS95% CI ±12
- 28
1,17495% CI ±10
- 29
1,16195% CI ±12
- 30
1,158Murf AI: Falcon 2Falcon 295% CI ±12
- 31
1,155Murf AI: Falcon 2.1Falcon 2.195% CI ±15
- 32
1,151 - 33
1,147Microsoft: Azure HD 2.5Azure HD 2.595% CI ±11
- 34A1,140async: Async Flash v1.5Async Flash v1.5
95% CI ±11
- 35
1,137StepFun: Step TTS 2Step TTS 295% CI ±11
- 36A1,129async: Async Pro v1.0Async Pro v1.0
95% CI ±11
- 37
1,12495% CI ±10
- 38
1,123 - 39
1,115SpeechifyAI: Simba 3.0Simba 3.095% CI ±11
- 40
1,114Rime: Coda v2Coda v295% CI ±13
- 41
1,111Resemble AI: Chatterbox HDChatterbox HD95% CI ±11
- 42
1,111Gradium: Phonon 31MPhonon 31M95% CI ±13
- 43
1,10995% CI ±11
- 44
1,104Fish Audio: Fish Audio S2 ProFish Audio S2 Pro95% CI ±11
- 45
1,10395% CI ±10
- 46
1,100StepFun: Step Audio EditXStep Audio EditX95% CI ±12
- 47
1,094ElevenLabs: Turbo v2.5Turbo v2.595% CI ±10
- 48
1,093ElevenLabs: Multilingual v2Multilingual v295% CI ±10
- 49
1,093Mistral: Voxtral TTSVoxtral TTS95% CI ±11
- 50
1,09195% CI ±11
Source: Artificial Analysis · arena Elo rating, as of Nov 16, 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.
