# Transcription en anglais, indice AA-WER, édition du 9 novembre 2026

Tableau repris tel que Artificial Analysis le publie : taux d'erreur par mot en anglais, indice AA-WER : moyenne pondérée de leur jeu privé d'agents vocaux AA-AgentTalk (50 %), de VoxPopuli (25 %) et d'Earnings22 (25 %), plus bas est meilleur. Aucun score de QUELLE IA, aucun score combiné. Édition du 9 novembre 2026.

| Rang | Modèle | Éditeur | Valeur (%) |
| ---: | --- | --- | --- |
| 1 | [Fun-Realtime-ASR-preview](https://quelleia.com/voix/modeles/alibaba-fun-realtime-asr-preview/) | Alibaba | 1,73 |
| 2 | [MAI-Transcribe-2](https://quelleia.com/voix/modeles/microsoft-mai-transcribe-2/) | Microsoft | 2,04 |
| 3 | [Voxtral Small Transcribe 3](https://quelleia.com/voix/modeles/voxtral-small-transcribe-3/) | Mistral AI | 2,09 |
| 4 | [Scribe v2](https://quelleia.com/voix/modeles/scribe-v2/) | ElevenLabs | 2,18 |
| 5 | [Voxtral Mini Transcribe 3](https://quelleia.com/voix/modeles/voxtral-mini-transcribe-3/) | Mistral AI | 2,22 |
| 6 | [Grok Voice Transcribe 2.0](https://quelleia.com/voix/modeles/spacexai-grok-voice-transcribe-2-0/) | SpaceXSI | 2,29 |
| 7 | [MAI-Transcribe-1.5](https://quelleia.com/voix/modeles/microsoft-mai-transcribe-1-5/) | Microsoft | 2,38 |
| 8 | [StepAudio 3 ASR](https://quelleia.com/voix/modeles/stepaudio-3-asr/) | StepFun | 2,50 |
| 9 | [Gemini 3.5 Transcribe](https://quelleia.com/voix/modeles/google-gemini-3-5-transcribe/) | Google | 2,60 |
| 10 | [Zoom Scribe V2 Pro](https://quelleia.com/voix/modeles/zoom-scribe-v2-pro/) | Zoom | 2,75 |
| 11 | [Voxtral Small](https://quelleia.com/voix/modeles/voxtral-small/) | Mistral AI | 2,77 |
| 12 | [Gemini 3.1 Pro Preview (High)](https://quelleia.com/voix/modeles/google-gemini-3-1-pro-preview-high/) | Google | 2,82 |
| 13 | [Gemini 2.5 Pro](https://quelleia.com/voix/modeles/google-gemini-2-5-pro/) | Google | 2,86 |
| 14 | [Gemini 3 Flash (High)](https://quelleia.com/voix/modeles/google-gemini-3-flash-high/) | Google | 2,93 |
| 15 | [Universal-3.5 Pro](https://quelleia.com/voix/modeles/assemblyai-universal-3-5-pro/) | AssemblyAI | 2,99 |
| 16 | [Universal-3 Pro](https://quelleia.com/voix/modeles/universal-3-pro/) | AssemblyAI | 3,12 |
| 17 | [Solaria-3](https://quelleia.com/voix/modeles/solaria-3/) | Gladia | 3,23 |
| 18 | [GPT Transcribe](https://quelleia.com/voix/modeles/gpt-transcribe/) | OpenAI | 3,31 |
| 19 | [Smallest AI Pulse](https://quelleia.com/voix/modeles/smallest-ai-pulse/) | Smallest AI | 3,33 |
| 20 | [Resonant-1](https://quelleia.com/voix/modeles/resonant-1/) | Reson8 | 3,39 |
| 21 | [Smallest AI Pulse Pro](https://quelleia.com/voix/modeles/smallest-ai-pulse-pro/) | Smallest AI | 3,41 |
| 22 | [Gemini 3.1 Flash-Lite Preview (Minimal)](https://quelleia.com/voix/modeles/google-gemini-3-1-flash-lite-preview-minimal/) | Google | 3,43 |
| 23 | [Qwen3.5 Omni Plus](https://quelleia.com/voix/modeles/alibaba-qwen3-5-omni-plus/) | Alibaba | 3,55 |
| 24 | [Gemini 3.1 Pro Preview (Low)](https://quelleia.com/voix/modeles/google-gemini-3-1-pro-preview-low/) | Google | 3,58 |
| 25 | [Voxtral Mini Transcribe 2](https://quelleia.com/voix/modeles/voxtral-mini-transcribe-2/) | Mistral AI | 3,59 |
| 26 | [Soniox v5 Async](https://quelleia.com/voix/modeles/soniox-v5-async/) | Soniox | 3,81 |
| 27 | [Universal](https://quelleia.com/voix/modeles/assemblyai-universal/) | AssemblyAI | 3,82 |
| 28 | [Voxtral Mini Transcribe](https://quelleia.com/voix/modeles/mistral-ai-voxtral-mini-transcribe/) | Mistral AI | 3,84 |
| 29 | [Inworld STT 1](https://quelleia.com/voix/modeles/inworld-stt-1/) | Inworld AI | 3,93 |
| 30 | [GPT-4o Transcribe](https://quelleia.com/voix/modeles/openai-gpt-4o-transcribe/) | OpenAI | 3,96 |
| 31 | [Speechmatics Enhanced](https://quelleia.com/voix/modeles/speechmatics-enhanced/) | Speechmatics | 4,05 |
| 32 | [Whisper Large v2](https://quelleia.com/voix/modeles/openai-whisper-large-v2/) | OpenAI | 4,06 |
| 33 | [Solaria-1](https://quelleia.com/voix/modeles/solaria-1/) | Gladia | 4,07 |
| 33 | [Whisper Large v3](https://quelleia.com/voix/modeles/whisper-large-v3/) | OpenAI | 4,07 |
| 35 | [Amazon Transcribe](https://quelleia.com/voix/modeles/amazon-transcribe/) | Amazon | 4,12 |
| 36 | [Modulate STT Batch English VFast](https://quelleia.com/voix/modeles/modulate-stt-batch-english-vfast/) | Modulate | 4,23 |
| 37 | [Canary Qwen 2.5B](https://quelleia.com/voix/modeles/canary-qwen-2-5b/) | NVIDIA | 4,27 |
| 38 | [Chirp 3](https://quelleia.com/voix/modeles/google-chirp-3/) | Google | 4,32 |
| 39 | [GPT-4o Mini Transcribe](https://quelleia.com/voix/modeles/openai-gpt-4o-mini-transcribe/) | OpenAI | 4,47 |
| 40 | [Parakeet TDT 0.6B V3](https://quelleia.com/voix/modeles/nvidia-parakeet-tdt-0-6b-v3/) | NVIDIA | 4,55 |
| 41 | [Cohere Transcribe](https://quelleia.com/voix/modeles/cohere-transcribe/) | Cohere | 4,57 |
| 42 | [Whisper Large v3 Turbo](https://quelleia.com/voix/modeles/whisper-large-v3-turbo/) | OpenAI | 4,62 |
| 43 | [StepAudio 2.5 ASR](https://quelleia.com/voix/modeles/stepaudio-2-5-asr/) | StepFun | 4,67 |
| 44 | [Nova 2 Pro](https://quelleia.com/voix/modeles/amazon-nova-2-pro/) | Amazon | 4,86 |
| 45 | [Melia](https://quelleia.com/voix/modeles/speechmatics-melia/) | Speechmatics | 4,87 |
| 46 | [Speechmatics Standard](https://quelleia.com/voix/modeles/speechmatics-standard/) | Speechmatics | 5,12 |
| 47 | [Gemini 2.5 Flash](https://quelleia.com/voix/modeles/google-gemini-2-5-flash/) | Google | 5,14 |
| 48 | [Gemini 2.5 Lite](https://quelleia.com/voix/modeles/google-gemini-2-5-lite/) | Google | 5,17 |
| 49 | [Nova-3](https://quelleia.com/voix/modeles/deepgram-nova-3/) | Deepgram | 5,18 |
| 50 | [Parakeet RNNT 1.1B](https://quelleia.com/voix/modeles/nvidia-parakeet-rnnt-1-1b/) | NVIDIA | 5,42 |
| 51 | [Rev AI](https://quelleia.com/voix/modeles/rev-ai/) | Rev | 5,92 |
| 52 | [Parakeet TDT 0.6B V2](https://quelleia.com/voix/modeles/parakeet-tdt-0-6b-v2/) | NVIDIA | 6,43 |
| 53 | [Gradium Speech-to-Text](https://quelleia.com/voix/modeles/gradium-speech-to-text/) | Gradium | 6,79 |
| 54 | [Qwen3.5 Omni Flash](https://quelleia.com/voix/modeles/alibaba-qwen3-5-omni-flash/) | Alibaba | 13,52 |
| 55 | [Cloud Speech-To-Text (Chirp)](https://quelleia.com/voix/modeles/google-cloud-speech-to-text-chirp/) | Google | 31,21 |

- Source : Artificial Analysis : https://artificialanalysis.ai/speech-to-text/non-streaming (relevé du 9 novembre 2026)

Source : QUELLE IA, édition du 9 novembre 2026, quelleia.com, d'après Artificial Analysis.