{"id":"speechmatics-enhanced","nom":"Speechmatics Enhanced","editeur":"Speechmatics","pays":"Royaume-Uni","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://docs.speechmatics.com/speech-to-text/models","essayer":"https://portal.speechmatics.com/"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/speechmatics-enhanced/","releve":"2026-10-19","en_bref":"16e sur 39 en transcription en français ; 28e sur 51 en transcription en anglais (Artificial Analysis).","presentation":"Enhanced est le modèle de transcription de Speechmatics réglé pour la précision maximale, en temps réel comme en différé, avec une variante médicale. L'éditeur le conseille pour l'audio d'une seule langue en médecine, en droit ou en sous-titrage.","langues":{"annoncees":{"annoncees":"plus de 55 langues, dont le français","nombre":55,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://docs.speechmatics.com/speech-to-text/models (« Enhanced and Standard are feature-identical and differ only in accuracy and speed: Enhanced delivers the highest accuracy, and Standard prioritizes throughput. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.speechmatics.com/speech-to-text/models (« Use Enhanced for the highest accuracy on single-language audio, such as medical, legal, or subtitling work. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.speechmatics.com/speech-to-text/models (« Enhanced, Standard, and Melia 1 are available for Realtime and Batch transcription. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.speechmatics.com/speech-to-text/languages (« The languages, packs, and options on this page apply to the Enhanced and Standard models. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.speechmatics.com/speech-to-text/languages (« French fr Global French gives high-accuracy transcription across many accents »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.speechmatics.com/ (« 55+ languages We cover over half the world's population with our language coverage »), 17/10/2026"}],"classements":[{"id":"transcription/francais","nom":"Transcription en français","rang":16,"sur":39,"valeur":4.89,"unite":"%","chiffres":{"jeux":{"Common Voice":5.7,"FLEURS":4.37,"MLS":4.61}},"voisins":["gpt-transcribe","microsoft-phi-4-multimodal-instruct"],"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/artificial-analysis","nom":"Transcription en anglais, indice AA-WER","rang":28,"sur":51,"valeur":4.05,"unite":"%","chiffres":{"prix_pour_1000_minutes":12.5,"jeux":{"AA-AgentTalk":3.38,"Earnings22":6.59,"VoxPopuli":2.86},"date_sortie":"2023-03-07","hebergeur":"Speechmatics"},"voisins":["openai-gpt-4o-transcribe","openai-whisper-large-v2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-text/models/speechmatics","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"speechmatics/enhanced","artificial_analysis":"Speechmatics Enhanced"}}