{"id":"gpt-transcribe","nom":"GPT Transcribe","editeur":"OpenAI","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://developers.openai.com/api/docs/models/gpt-transcribe","essayer":"https://developers.openai.com/api/docs/guides/speech-to-text"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/gpt-transcribe/","releve":"2026-10-19","en_bref":"15e sur 39 en transcription en français ; 16e sur 51 en transcription en anglais (Artificial Analysis) ; 19e sur 53 en transcription en anglais (Open ASR) (ex æquo à valeur égale).","presentation":"Modèle de transcription d'OpenAI, servi par son API, pour les fichiers audio terminés et les tours de parole validés dans une session temps réel. Il accepte un contexte libre, des mots-clés et plusieurs langues attendues pour mieux traiter le vocabulaire métier et les enregistrements qui mêlent les langues.","sortie":"2026-07-28","langues":{"annoncees":{"annoncees":"multilingue, nombre de langues non publié ; le français est cité","francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-transcribe.md (« GPT Transcribe is a speech-to-text model for completed audio files, streamed file transcripts, and committed turns in Realtime sessions over WebSocket. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-transcribe.md (« It supports unstructured context, keyword hints, and multiple language hints to improve transcription of domain terms, multilingual audio, and code-switching. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://developers.openai.com/api/docs/changelog.md (« ### Jul 28 Feature · Model: gpt-transcribe · Model: gpt-live-transcribe »), 17/10/2026"},{"appuie":["langues"],"lu":"https://developers.openai.com/api/docs/guides/speech-to-text.md (« ISO 639-1 codes, such as `en`, `es`, and `fr`. »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":15,"sur":39,"valeur":4.82,"unite":"%","chiffres":{"jeux":{"Common Voice":6.97,"FLEURS":3.45,"MLS":4.05}},"voisins":["nvidia-canary-1b-v2","speechmatics-enhanced"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}},{"id":"transcription/artificial-analysis","nom":"Transcription en anglais, indice AA-WER","rang":16,"sur":51,"valeur":3.31,"unite":"%","chiffres":{"prix_pour_1000_minutes":4.5,"jeux":{"AA-AgentTalk":2.22,"Earnings22":6.1,"VoxPopuli":2.72},"hebergeur":"OpenAI"},"voisins":["solaria-3","smallest-ai-pulse"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-text/models/openai-gpt-transcribe","releve":"2026-10-19"}},{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":19,"sur":53,"valeur":5.96,"unite":"%","chiffres":{"jeux":{"AMI-Cleaned":8.95,"Earnings22-Cleaned-AA-chunked":6.61,"Gigaspeech-Cleaned":7.76,"LS Clean":1.31,"LS Other":3.39,"Private (conversational)":12.9,"Private (scripted)":3.24,"SPGISpeech":2.23,"URGENT24":12.86,"Voice Arena Monsoon":3.63,"Voxpopuli-AA-Cleaned":2.65}},"voisins":["canary-qwen-2-5b","ibm-granite-speech-4-1-2b"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"openai/gpt-transcribe","artificial_analysis":"GPT Transcribe"}}