{"id":"bland-speech-v3","nom":"Bland Speech v3","editeur":"Bland AI","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://www.bland.ai/speech","essayer":"https://docs.bland.ai/tts/welcome"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/bland-speech-v3/","releve":"2026-10-19","en_bref":"69e 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":"Premier modèle de la plateforme de synthèse vocale Bland Speech, entraîné sur de vraies conversations pour garder les respirations, hésitations et pauses de la parole humaine. Il est servi par l'API /v1/speak en flux continu, avec clonage de voix à partir d'environ 10 secondes d'audio.","sortie":"2026-08-04","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://www.bland.ai/blog/bland-speech-v3-audio-realism-bench (« Introducing Bland Speech v3: The first Human Speech Engine A text-to-speech platform trained on real human conversations »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://www.bland.ai/blog/bland-speech-v3-audio-realism-bench (« Cole Baker August 4, 2026 »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://www.bland.ai/blog/bland-speech-v3-audio-realism-bench (« Today, we’re introducing Bland Speech, a TTS platform for developers building real-time voice applications. We are launching with our first model and will add new models over time. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.bland.ai/speech (« It keeps the breaths, stumbles and pauses real people make. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.bland.ai/speech (« Yes. 10 seconds of audio gets an instant clone. 30 minutes of verified audio gets a professional clone. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.bland.ai/speech (« POST your text to /v1/speak with an API key. Audio streams back over HTTP chunks or a WebSocket. »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":69,"sur":96,"valeur":1038.62,"unite":"Elo","bas":1025.62,"haut":1051.62,"votes":2443,"chiffres":{"prix_par_million_caracteres":40,"date_sortie":"2026-08-05"},"voisins":["boson-ai-higgs-tts-3-4b","hume-ai-octave-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/bland-btts","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Bland Speech v3"}}