{"id":"openai-tts-1","nom":"TTS-1","editeur":"OpenAI","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://developers.openai.com/api/docs/models/tts-1","essayer":"https://developers.openai.com/api/docs/guides/text-to-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/openai-tts-1/","releve":"2026-10-19","en_bref":"44e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 10 modèles trop proches pour être départagés.","presentation":"Modèle de synthèse vocale d'OpenAI, servi par l'API Audio, réglé pour une faible latence. Il offre neuf voix prédéfinies, avec une qualité moindre que TTS-1 HD.","langues":{"annoncees":{"annoncees":"57 langues, comme Whisper, dont le français","nombre":57,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/models/tts-1.md (« The tts-1 model is optimized for realtime text-to-speech use cases. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/guides/text-to-speech.md (« Our other text-to-speech models are `tts-1` and `tts-1-hd`. The `tts-1` model provides lower latency, but at a lower quality than the `tts-1-hd` model. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://developers.openai.com/api/docs/guides/text-to-speech.md (« The `tts-1` and `tts-1-hd` models support a smaller set: `alloy`, `ash`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, and `shimmer`. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://developers.openai.com/api/docs/guides/text-to-speech.md (« The TTS model generally follows the Whisper model in terms of language support. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://developers.openai.com/api/docs/guides/text-to-speech.md (« Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":44,"sur":96,"valeur":1090.18,"unite":"Elo","bas":1079.18,"haut":1101.18,"votes":6237,"chiffres":{"prix_par_million_caracteres":15,"date_sortie":"2023-11-06"},"voisins":["minimax-speech-02-turbo","voxtral-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/openai","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"TTS-1"}}