{"id":"voxtral-mini-transcribe-2","nom":"Voxtral Mini Transcribe 2","editeur":"Mistral AI","pays":"France","poids_ouverts":true,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://docs.mistral.ai/models/voxtral-mini-transcribe-26-02","essayer":"https://docs.mistral.ai/studio/audio/speech_to_text"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/voxtral-mini-transcribe-2/","releve":"2026-10-19","en_bref":"23e sur 51 en transcription en anglais (Artificial Analysis).","presentation":"Modèle de transcription par lots de Mistral AI, servi par son API, avec identification des locuteurs, horodatage mot à mot et liste de termes pour guider l'orthographe des noms propres. Il accepte des enregistrements jusqu'à trois heures en une requête.","sortie":"2026-02-04","langues":{"annoncees":{"annoncees":"13 langues, dont le français","nombre":13,"francais":true,"liste":["en","zh","hi","es","ar","fr","pt","ru","de","ja","ko","it","nl"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["sortie"],"lu":"https://mistral.ai/news/voxtral-transcribe-2 (« Voxtral transcribes at the speed of sound. February 4, 2026 By Mistral »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://mistral.ai/news/voxtral-transcribe-2 (« Voxtral Mini Transcribe V2: State-of-the-art transcription with speaker diarization, context biasing, and word-level timestamps in 13 languages. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://mistral.ai/news/voxtral-transcribe-2 (« Like Realtime, this model now supports 13 languages: English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://mistral.ai/news/voxtral-transcribe-2 (« Longer audio support. Process recordings up to 3 hours in a single request. »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://docs.mistral.ai/models/voxtral-mini-transcribe-26-02 (« February 4, 2026 Blog GA Premier v 26.02 Voxtral Mini Transcribe 2 An efficient audio input model, pre-trained and optimized for transcription purposes only. »), 17/10/2026"}],"classements":[{"id":"transcription/artificial-analysis","nom":"Transcription en anglais, indice AA-WER","rang":23,"sur":51,"valeur":3.59,"unite":"%","chiffres":{"prix_pour_1000_minutes":3,"jeux":{"AA-AgentTalk":2.96,"Earnings22":6.28,"VoxPopuli":2.16},"date_sortie":"2026-02-04","hebergeur":"Mistral"},"voisins":["google-gemini-3-1-pro-preview-low","soniox-v5-async"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-text/models/mistral","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Voxtral Mini Transcribe 2"}}