# Synthèse vocale en anglais, TTS Arena, édition du 9 novembre 2026

Tableau repris tel que TTS Arena V2 le publie : préférences d'internautes à l'aveugle entre deux voix qui lisent la même phrase en anglais. Aucun score de QUELLE IA, aucun score combiné. Édition du 9 novembre 2026.

| Rang | Modèle | Éditeur | Valeur (Elo) |
| ---: | --- | --- | --- |
| 1 | [CastleFlow v1.0](https://quelleia.com/voix/modeles/castleflow-v1-0/) | Async | 1 556 |
| 2 | [Inworld TTS MAX](https://quelleia.com/voix/modeles/inworld-tts-max/) | Inworld AI | 1 554 |
| 3 | [Aurora](https://quelleia.com/voix/modeles/aurora/) |  | 1 562 |
| 4 | [Papla P1](https://quelleia.com/voix/modeles/papla-p1/) | Papla Media | 1 545 |
| 5 | [Inworld TTS](https://quelleia.com/voix/modeles/inworld-tts/) | Inworld AI | 1 538 |
| 6 | [star-june-2026](https://quelleia.com/voix/modeles/star-june-2026/) |  | 1 548 |
| 7 | [MiniMax Speech 2.8 HD](https://quelleia.com/voix/modeles/minimax-speech-2-8-hd/) | MiniMax | 1 535 |
| 8 | [Hume Octave](https://quelleia.com/voix/modeles/hume-octave/) | Hume AI | 1 522 |
| 9 | [Lightning v3.1 Pro](https://quelleia.com/voix/modeles/smallest-ai-lightning-v3-1-pro/) | Smallest AI | 1 527 |
| 10 | [Gradium TTS (pre-2026.08)](https://quelleia.com/voix/modeles/gradium-tts-pre-2026-08/) | Gradium | 1 521 |
| 11 | [MiniMax Speech 02 HD](https://quelleia.com/voix/modeles/minimax-speech-02-hd/) | MiniMax | 1 509 |
| 12 | [MiniMax Speech 2.8 Turbo](https://quelleia.com/voix/modeles/minimax-speech-2-8-turbo/) | MiniMax | 1 519 |
| 13 | [MiniMax Speech 2.6 Turbo](https://quelleia.com/voix/modeles/minimax-speech-2-6-turbo/) | MiniMax | 1 516 |
| 14 | [OpenAudio S2](https://quelleia.com/voix/modeles/fish-audio-openaudio-s2/) | Fish Audio | 1 515 |
| 15 | [Inworld TTS 1.5 MAX](https://quelleia.com/voix/modeles/inworld-tts-1-5-max/) | Inworld AI | 1 513 |
| 16 | [Deepdub eTTS 3.2](https://quelleia.com/voix/modeles/deepdub-etts-3-2/) | Deepdub | 1 522 |
| 17 | [Eleven Flash v2.5](https://quelleia.com/voix/modeles/elevenlabs-flash-v2-5/) | ElevenLabs | 1 505 |
| 18 | [Eleven Multilingual v2](https://quelleia.com/voix/modeles/elevenlabs-multilingual-v2/) | ElevenLabs | 1 504 |
| 19 | [MiniMax Speech 02 Turbo](https://quelleia.com/voix/modeles/minimax-speech-02-turbo/) | MiniMax | 1 501 |
| 20 | [Eleven Turbo v2.5](https://quelleia.com/voix/modeles/elevenlabs-turbo-v2-5/) | ElevenLabs | 1 504 |
| 21 | [Parmesan](https://quelleia.com/voix/modeles/parmesan/) |  | 1 498 |
| 22 | [Cartesia Sonic 2](https://quelleia.com/voix/modeles/cartesia-sonic-2/) | Cartesia | 1 503 |
| 23 | [OpenAudio S1](https://quelleia.com/voix/modeles/openaudio-s1/) | Fish Audio | 1 503 |
| 24 | [Hithink Speech 2.6](https://quelleia.com/voix/modeles/hithink-speech-2-6-2/) | HiThink | 1 500 |
| 25 | [Typecast SSFM 3.0](https://quelleia.com/voix/modeles/typecast-ssfm-3-0/) | Neosapience | 1 500 |
| 26 | [MiniMax Speech 2.6 HD](https://quelleia.com/voix/modeles/minimax-speech-2-6-hd/) | MiniMax | 1 500 |
| 27 | [Eleven v3](https://quelleia.com/voix/modeles/elevenlabs-eleven-v3/) | ElevenLabs | 1 498 |
| 28 | [Chatterbox](https://quelleia.com/voix/modeles/chatterbox/) | Resemble AI | 1 475 |
| 29 | [Kokoro 82M v1.0](https://quelleia.com/voix/modeles/kokoro-82m-v1-0/) | hexgrad | 1 473 |
| 30 | [Tontaube V0](https://quelleia.com/voix/modeles/tontaube-v0/) | Tontaube | 1 480 |
| 31 | [Voice.ai Text to Speech V1](https://quelleia.com/voix/modeles/voice-ai-text-to-speech-v1/) | Voice.ai | 1 475 |
| 32 | [Magpie Research Preview](https://quelleia.com/voix/modeles/magpie-research-preview/) | NVIDIA | 1 470 |
| 33 | [NeuTTS Max](https://quelleia.com/voix/modeles/neutts-max/) | Neuphonic | 1 435 |
| 34 | [Magpie Multilingual](https://quelleia.com/voix/modeles/magpie-multilingual/) | NVIDIA | 1 402 |
| 35 | [Maya1](https://quelleia.com/voix/modeles/maya1/) | Maya Research | 1 407 |
| 36 | [Fluxions Vui](https://quelleia.com/voix/modeles/fluxions-vui/) |  | 1 437 |
| 37 | [Silk Mulberry 1.5](https://quelleia.com/voix/modeles/silk-mulberry-1-5/) | rumik | 1 410 |
| 38 | [Wordcab TTS](https://quelleia.com/voix/modeles/wordcab-tts/) | Wordcab | 1 357 |
| 39 | [Veena](https://quelleia.com/voix/modeles/veena/) | Maya Research | 1 360 |
| 40 | [Tontaube V1](https://quelleia.com/voix/modeles/tontaube-v1/) |  | 1 377 |

- Source : TTS Arena V2, TTS-AGI : https://huggingface.co/spaces/TTS-AGI/TTS-Arena-V2 (relevé du 9 novembre 2026)

Source : QUELLE IA, édition du 9 novembre 2026, quelleia.com, d'après TTS Arena V2.