{"id":"hume-ai-octave-tts","nom":"Octave TTS","editeur":"Hume AI","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://dev.hume.ai/docs/text-to-speech-tts/overview","essayer":"https://dev.hume.ai/reference/text-to-speech-tts/synthesize-json"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/hume-ai-octave-tts/","releve":"2026-10-19","en_bref":"69e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 12 modèles trop proches pour être départagés.","presentation":"Modèle de synthèse vocale Octave de Hume AI dans sa première version, lancée en février 2025. Il ajuste prononciation, hauteur, débit et accentuation selon l'intention émotionnelle de chaque mot, clone une voix à partir de 15 secondes d'audio et crée des voix sur description.","sortie":"2025-02-26","langues":{"annoncees":{"annoncees":"2 langues (anglais, espagnol)","nombre":2,"francais":false,"liste":["en","es"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://www.hume.ai/blog/octave-the-first-text-to-speech-model-that-understands-what-its-saying (« Octave TTS: the first text-to-speech system that understands what it’s saying »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://www.hume.ai/blog/octave-the-first-text-to-speech-model-that-understands-what-its-saying (« Hume AI Team February 26, 2025 Share Today we’re launching Octave (Omni-capable text and voice engine), the first LLM for text-to-speech. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://dev.hume.ai/docs/text-to-speech-tts/overview (« it adapts pronunciation, pitch, tempo, and emphasis to match each word’s emotional intent. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://dev.hume.ai/docs/text-to-speech-tts/overview (« Octave can create a high-quality voice clone using as little as 15 seconds of audio. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://dev.hume.ai/docs/text-to-speech-tts/overview (« Octave versions Feature Octave 1 Octave 2 (preview) Supported languages English, Spanish »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":69,"sur":96,"valeur":1039.19,"unite":"Elo","bas":1028.19,"haut":1050.19,"votes":4699,"chiffres":{"prix_par_million_caracteres":87.5,"date_sortie":"2025-02-26"},"voisins":["bland-speech-v3","google-gemini-2-5-pro-dec-2025"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/humeai","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Octave TTS"}}