{"id":"openai-gpt-realtime","nom":"GPT-Realtime","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-realtime","essayer":"https://developers.openai.com/api/docs/guides/realtime"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/openai-gpt-realtime/","releve":"2026-11-09","en_bref":"10e sur 12 à l'indice voix à voix d'Artificial Analysis ; 21e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 14e sur 31 en tenue de la conversation (Full Duplex Bench) ; 17e sur 34 au délai avant le premier son.","presentation":"Premier modèle temps réel d'OpenAI sorti de la préversion, qui répond à la voix et au texte en direct par WebRTC, WebSocket ou SIP. Sa version de référence date du 28 août 2025.","sortie":"2025-08-28","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-realtime.md (« This is our first general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections. »), 23/10/2026"},{"appuie":["sortie","presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-realtime.md (« Default snapshot: `gpt-realtime-2025-08-28` »), 23/10/2026"},{"appuie":["sortie"],"lu":"https://developers.openai.com/api/docs/changelog.md (« ### Aug 28 Feature · API: v1/realtime The OpenAI Realtime API is now generally available. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":10,"sur":12,"valeur":69.19,"unite":"points","chiffres":{"cout_par_heure_audio_entree":11.08328599765094,"hebergeur":"OpenAI"},"voisins":["google-gemini-3-1-flash-live-preview","openai-gpt-realtime-2-1-mini"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}},{"id":"voix-a-voix/raisonnement","nom":"Raisonnement à l'écoute, Big Bench Audio","rang":21,"sur":38,"valeur":83.3,"unite":"%","chiffres":{"cout_par_heure_audio_entree":11.08328599765094,"hebergeur":"OpenAI"},"voisins":["deepslate-opal","openai-gpt-realtime-1-5"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}},{"id":"voix-a-voix/conversation","nom":"Tenue de la conversation, Full Duplex Bench","rang":14,"sur":31,"valeur":93.86,"unite":"%","chiffres":{"cout_par_heure_audio_entree":11.08328599765094,"hebergeur":"OpenAI"},"voisins":["elevenlabs-eleven-realtime-v1-max","boson-ai-higgs-realtime"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}},{"id":"voix-a-voix/delai","nom":"Délai avant le premier son","rang":17,"sur":34,"valeur":0.98,"unite":"s","chiffres":{"cout_par_heure_audio_entree":11.08328599765094,"hebergeur":"OpenAI"},"voisins":["openai-gpt-realtime-2-1","openai-gpt-realtime-2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}}],"noms_dans_les_sources":{"aa_voix_a_voix":"GPT Realtime (Aug '25)"}}