{"id":"openai-gpt-live-1","nom":"GPT-Live 1","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-live-1","essayer":"https://developers.openai.com/api/docs/guides/live"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/openai-gpt-live-1/","releve":"2026-11-09","en_bref":"1er sur 12 à l'indice voix à voix d'Artificial Analysis ; 18e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 3e sur 31 en tenue de la conversation (Full Duplex Bench) ; 21e sur 34 au délai avant le premier son.","presentation":"Modèle vocal d'OpenAI en duplex intégral, qui écoute et parle en même temps et confie le raisonnement et les outils à un modèle ou un agent en arrière-plan. Il est servi par l'API Live et facturé à la minute de conversation.","sortie":"2026-09-10","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-live-1.md (« GPT-Live 1 is a full-duplex voice model for real-time conversations. It can listen and speak at the same time, and delegate reasoning and tool use to a backend agent. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-live-1.md (« Voice sessions cost $0.05 per minute, billed per second. Backend model and tool usage is billed separately. »), 23/10/2026"},{"appuie":["sortie"],"lu":"https://developers.openai.com/api/docs/changelog.md (« ### Sep 10 Feature · Model: gpt-live-1 · API: v1/live/sessions [GPT-Live 1](https://developers.openai.com/api/docs/models/gpt-live-1) is now generally available in the API. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/guides/live-delegation.md (« Add this delegation configuration when [creating your Live session](https://developers.openai.com/api/docs/guides/live). Choose the Responses model independently of the voice model: »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/guides/live-delegation.md (« `reasoning.effort`: balance reasoning time and task quality using values supported by that model. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models.md (« If you're not sure where to start, use [GPT-6 Astra](/api/docs/models/gpt-6-astra), our flagship model for complex reasoning and coding. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":1,"sur":12,"valeur":84.3,"unite":"points","chiffres":{"cout_par_heure_audio_entree":5.828694020396,"hebergeur":"OpenAI"},"voisins":["alibaba-qwen-audio-3-0-realtime-plus"],"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":18,"sur":38,"valeur":90.1,"unite":"%","chiffres":{"cout_par_heure_audio_entree":5.828694020396,"hebergeur":"OpenAI"},"voisins":["google-gemini-2-5-flash-native-audio-dialog-thinking","amazon-nova-2-sonic"],"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":3,"sur":31,"valeur":97.27,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.4655296763872,"hebergeur":"OpenAI"},"voisins":["alibaba-qwen-audio-3-0-realtime-plus","spacexai-grok-voice-3-0"],"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":21,"sur":34,"valeur":1.236,"unite":"s","chiffres":{"cout_par_heure_audio_entree":4.4655296763872,"hebergeur":"OpenAI"},"voisins":["google-gemini-3-8-live","spacexai-grok-voice-1-0"],"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-Live-1 (Astra, medium)"}}