{"id":"spacexai-grok-voice-2-0","nom":"Grok Voice 2.0","editeur":"SpaceXSI","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://x.ai/news/grok-voice-think-fast-2","essayer":"https://docs.x.ai/developers/model-capabilities/audio/speech-to-speech"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/spacexai-grok-voice-2-0/","releve":"2026-11-09","en_bref":"3e sur 12 à l'indice voix à voix d'Artificial Analysis ; 9e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 12e sur 31 en tenue de la conversation (Full Duplex Bench) ; 7e sur 34 au délai avant le premier son.","presentation":"Deuxième génération du modèle parole à parole de SpaceXSI, qui raisonne en parlant, avec une meilleure transcription et des appels d'outils plus fiables que Grok Voice 1.0. Elle est dépréciée depuis la sortie de Grok Voice 3.0.","sortie":"2026-07-29","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation","sortie"],"lu":"https://x.ai/news/grok-voice-think-fast-2 (« Jul 29, 2026 Introducing Grok Voice 2.0 Introducing our most capable speech-to-speech voice model. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://x.ai/news/grok-voice-think-fast-2 (« Grok Voice 2.0 is our most intelligent voice model yet, building on its predecessor with meaningful gains in speech reasoning, conversational ability, and tool use reliability. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://x.ai/news/grok-voice-think-fast-2 (« Grok Voice models have a unique characteristic: they reason through queries while speaking. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://docs.x.ai/developers/release-notes.md (« `grok-voice-2.0` is deprecated. To upgrade, set `model` to `grok-voice-3.0` or `grok-voice-latest`, at the same price. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":3,"sur":12,"valeur":82.93,"unite":"points","chiffres":{"cout_par_heure_audio_entree":4.8,"hebergeur":"SpaceXAI"},"voisins":["alibaba-qwen-audio-3-0-realtime-plus","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/raisonnement","nom":"Raisonnement à l'écoute, Big Bench Audio","rang":9,"sur":38,"valeur":97.2,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.8,"hebergeur":"SpaceXAI"},"voisins":["step-audio-r1-1-realtime","spacexai-grok-voice-1-0"],"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":12,"sur":31,"valeur":95.12,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.8,"hebergeur":"SpaceXAI"},"voisins":["openai-gpt-realtime-2-1","elevenlabs-eleven-realtime-v1-max"],"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":7,"sur":34,"valeur":0.7,"unite":"s","chiffres":{"cout_par_heure_audio_entree":4.8,"hebergeur":"SpaceXAI"},"voisins":["google-gemini-2-5-flash-native-audio-dialog","spacexai-grok-voice-fast-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":"Grok Voice 2.0"}}