{"id":"openai-gpt-realtime-1-5","nom":"GPT-Realtime-1.5","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-1.5","essayer":"https://developers.openai.com/api/docs/guides/realtime"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/openai-gpt-realtime-1-5/","releve":"2026-11-09","en_bref":"8e sur 12 à l'indice voix à voix d'Artificial Analysis ; 22e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 9e sur 31 en tenue de la conversation (Full Duplex Bench) (ex æquo à valeur égale) ; 10e sur 34 au délai avant le premier son (ex æquo à valeur égale).","presentation":"Modèle vocal d'OpenAI qui reçoit et produit de l'audio, servi par l'API Realtime et destiné aux agents vocaux et au service client. Il a été publié en février 2026, avant GPT-Realtime-2.","sortie":"2026-02-23","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-1.5.md (« GPT-Realtime-1.5 is our flagship audio model for voice agents and customer support. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-realtime-1.5.md (« The best voice model for audio in, audio out »), 23/10/2026"},{"appuie":["sortie"],"lu":"https://developers.openai.com/api/docs/changelog.md (« ### Feb 23 Feature · Model: gpt-realtime-1.5 · Model: gpt-audio-1.5 · API: v1/realtime · API: v1/chat/completions Released [GPT-Realtime-1.5](https://developers.openai.com/api/docs/models/gpt-realtime-1.5) to the Realtime API. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":8,"sur":12,"valeur":71.98,"unite":"points","chiffres":{"cout_par_heure_audio_entree":11.441296719440393,"hebergeur":"OpenAI"},"voisins":["spacexai-grok-voice-1-0","google-gemini-3-1-flash-live-preview"],"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":22,"sur":38,"valeur":81.4,"unite":"%","chiffres":{"cout_par_heure_audio_entree":11.441296719440393,"hebergeur":"OpenAI"},"voisins":["openai-gpt-realtime","elevenlabs-eleven-realtime-v1-mini"],"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":9,"sur":31,"valeur":95.7,"unite":"%","chiffres":{"cout_par_heure_audio_entree":11.441296719440393,"hebergeur":"OpenAI"},"voisins":["openai-gpt-realtime-mini","openai-gpt-realtime-2-1"],"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":10,"sur":34,"valeur":0.809,"unite":"s","chiffres":{"cout_par_heure_audio_entree":11.441296719440393,"hebergeur":"OpenAI"},"voisins":["openai-gpt-realtime-mini","spacexai-grok-voice-3-0"],"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-1.5"}}