{"id":"openai-gpt-realtime-2-1-mini","nom":"GPT-Realtime-2.1 Mini","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-2.1-mini","essayer":"https://developers.openai.com/api/docs/guides/realtime"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/openai-gpt-realtime-2-1-mini/","releve":"2026-11-09","en_bref":"11e sur 12 à l'indice voix à voix d'Artificial Analysis ; 24e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 17e sur 31 en tenue de la conversation (Full Duplex Bench) ; 13e sur 34 au délai avant le premier son.","presentation":"Version distillée de GPT-Realtime-2.1, plus rapide et moins chère, pour les échanges vocaux en temps réel. Elle raisonne avant de répondre et se connecte par WebRTC, WebSocket ou SIP.","sortie":"2026-07-06","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-2.1-mini.md (« GPT-Realtime-2.1 Mini is a distilled reasoning model for faster, lower-cost realtime voice interactions. It supports audio and text inputs over WebRTC, WebSocket, or SIP connections and improves alphanumeric recognition over GPT-Realtime-2. »), 23/10/2026"},{"appuie":["sortie","presentation"],"lu":"https://developers.openai.com/api/docs/changelog.md (« Also released [GPT-Realtime-2.1 mini](https://developers.openai.com/api/docs/models/gpt-realtime-2.1-mini), a faster, lower-cost distilled reasoning model for realtime voice applications. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":11,"sur":12,"valeur":59,"unite":"points","chiffres":{"cout_par_heure_audio_entree":4.596224401411048,"hebergeur":"OpenAI"},"voisins":["openai-gpt-realtime","openai-gpt-realtime-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":24,"sur":38,"valeur":74.7,"unite":"%","chiffres":{"cout_par_heure_audio_entree":3.451501405805465,"hebergeur":"OpenAI"},"voisins":["elevenlabs-eleven-realtime-v1-mini","openai-gpt-4o-mini-realtime"],"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":17,"sur":31,"valeur":91.77,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.596224401411048,"hebergeur":"OpenAI"},"voisins":["google-gemini-3-8-live-extended-thinking","nvidia-personaplex-7b-v1"],"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":13,"sur":34,"valeur":0.852,"unite":"s","chiffres":{"cout_par_heure_audio_entree":4.596224401411048,"hebergeur":"OpenAI"},"voisins":["spacexai-grok-voice-3-0","alibaba-qwen3-omni-30b-a3b-instruct-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-Realtime-2.1 Mini Minimal"}}