{"id":"xiaomi-mimo-v2-5-tts","nom":"MiMo-V2.5-TTS","editeur":"Xiaomi","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://mimo.xiaomi.com/mimo-v2-5-tts","essayer":"https://mimo.mi.com/static/docs/quick-start/usage-guide/audio/speech-synthesis-v2.5.md"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/xiaomi-mimo-v2-5-tts/","releve":"2026-10-19","en_bref":"62e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 12 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Modèle de synthèse vocale de Xiaomi à voix prédéfinies, servi par l'API MiMo, dont on règle le débit, l'émotion et le ton par instructions en langage naturel ou par balises audio dans le texte. Il forme une série avec deux variantes, l'une qui crée une voix à partir d'une description, l'autre qui clone une voix à partir de quelques échantillons.","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://mimo.xiaomi.com/mimo-v2-5-tts (« MiMo-V2.5-TTS Ships with a curated library of high-quality voices, paired with strong style-instruction following. Offers fine-grained control over pace, emotion, and tone »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://mimo.xiaomi.com/mimo-v2-5-tts (« the series ships three models - each targeting a distinct flavor of TTS need: premium stock voices, voice design, and voice cloning. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://mimo.xiaomi.com/mimo-v2-5-tts (« MiMo-V2.5-TTS-VoiceClone Faithfully reproduces a target voice from just a few audio samples »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://mimo.xiaomi.com/mimo-v2-5-tts (« Tags work in both Chinese and English and accept free-form descriptions »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://mimo.mi.com/static/docs/news/latest/v2.5-tts-release.md (« The MiMo-V2.5-TTS Series includes three models, which have now been launched on »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":62,"sur":96,"valeur":1053.66,"unite":"Elo","bas":1040.66,"haut":1066.66,"votes":2066,"voisins":["hume-ai-octave-2","deepgram-flux-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/mimo","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"MiMo-V2.5-TTS"}}