{"id":"modulate-multilingual","nom":"multilingual","editeur":"Modulate","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Open ASR Leaderboard","licence":null,"licence_selon":null,"liens":{"page":"https://docs.modulate.ai/get-started/stt","essayer":"https://docs.modulate.ai/quickstart"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/modulate-multilingual/","releve":"2026-10-19","en_bref":"12e sur 39 en transcription en français ; 4e sur 53 en transcription en anglais (Open ASR).","presentation":"Modulate publie sous le nom « multilingual » un modèle de transcription multilingue servi par son API, qui détecte la langue à chaque énoncé et suit les changements de langue. La version complète de l'éditeur ajoute séparation des orateurs, signaux d'émotion, d'accent, de voix synthétique et de données personnelles.","langues":{"annoncees":{"annoncees":"multilingue, dont le français","francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://docs.modulate.ai/get-started/stt.md (« * **Multilingual Transcription** carries per-utterance timing, speaker labels, and optional emotion, accent, deepfake, and PII/PHI signals. Batch and streaming. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.modulate.ai/get-started/stt.md (« Language is detected per utterance, so a file where speakers switch languages reports each utterance in the language actually spoken. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.modulate.ai/get-started/stt.md (« Multilingual Transcription covers 100 languages »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.modulate.ai/get-started/stt.md (« The 25 supported languages are Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.modulate.ai/api/speech-to-text (« Transcribe supports global coverage with over 50 languages covered. »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":12,"sur":39,"valeur":4.14,"unite":"%","chiffres":{"jeux":{"Common Voice":5.27,"FLEURS":4.71,"MLS":2.45}},"voisins":["voxtral-small","thestageai-thewhisper-large-v3-turbo"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}},{"id":"transcription/open-asr-anglais","nom":"Transcription en anglais, Open ASR","rang":4,"sur":53,"valeur":5.06,"unite":"%","chiffres":{"jeux":{"AMI-Cleaned":6.31,"Earnings22-Cleaned-AA-chunked":6,"Gigaspeech-Cleaned":6.91,"LS Clean":0.87,"LS Other":1.77,"Private (conversational)":12.3,"Private (scripted)":2.56,"SPGISpeech":2.06,"URGENT24":10.04,"Voice Arena Monsoon":3.26,"Voxpopuli-AA-Cleaned":3.55}},"voisins":["microsoft-azure-speech-07-2026","resonant-1"],"source":{"nom":"Open ASR Leaderboard","mention":"Source : Open ASR Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"modulate/multilingual"}}