{"id":"openai-gpt-4o-realtime","nom":"GPT-4o 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-4o-realtime-preview"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/openai-gpt-4o-realtime/","releve":"2026-11-09","en_bref":"19e sur 31 en tenue de la conversation (Full Duplex Bench) ; 26e sur 34 au délai avant le premier son.","presentation":"Préversion du modèle temps réel d'OpenAI fondé sur GPT-4o, qui répond à la voix et au texte par WebRTC ou WebSocket. La version classée ici est celle du 17 décembre 2024.","sortie":"2024-12-17","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview.md (« This is a preview release of the GPT-4o Realtime model, capable of responding to audio and text inputs in realtime over WebRTC or a WebSocket interface. »), 23/10/2026"},{"appuie":["sortie","presentation"],"lu":"https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview.md (« - `gpt-4o-realtime-preview-2024-12-17` »), 23/10/2026"},{"appuie":["sortie"],"lu":"https://developers.openai.com/api/docs/changelog.md (« ### Dec 17 Feature · Model: o1 · Model: gpt-4o · Model: gpt-4o-mini · API: v1/fine_tuning · API: v1/chat/completions · API: v1/realtime Added new models for [o1](https://developers.openai.com/api/docs/models/o1), [gpt-4o-realtime](https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview) »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/conversation","nom":"Tenue de la conversation, Full Duplex Bench","rang":19,"sur":31,"valeur":89.83,"unite":"%","chiffres":{"cout_par_heure_audio_entree":2.0433427044741306,"hebergeur":"OpenAI"},"voisins":["nvidia-personaplex-7b-v1","krafton-raon-speechchat-9b"],"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":26,"sur":34,"valeur":1.49,"unite":"s","chiffres":{"cout_par_heure_audio_entree":2.0433427044741306,"hebergeur":"OpenAI"},"voisins":["boson-ai-higgs-realtime","step-audio-r1-1-realtime"],"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-4o Realtime (Dec 2024)"}}