{"id":"spacexai-tts","nom":"SpaceXAI TTS","editeur":"SpaceXSI","pays":null,"poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://docs.x.ai/developers/model-capabilities/audio/text-to-speech","essayer":"https://docs.x.ai/developers/model-capabilities/audio/text-to-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/spacexai-tts/","releve":"2026-10-19","en_bref":"16e sur 31 en synthèse vocale en français, dans un groupe de 5 modèles trop proches pour être départagés ; 27e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 7 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"La synthèse vocale de l'API Grok convertit du texte en parole avec des voix expressives, des balises de jeu (rire, pause, chuchotement) et un flux continu par WebSocket. Elle accepte des voix clonées à partir d'un court extrait audio et n'expose pas de nom de modèle versionné.","sortie":"2026-03","langues":{"annoncees":{"annoncees":"20 langues, dont le français","nombre":20,"francais":true,"liste":["en","ar","bn","zh","fr","de","hi","id","it","ja","ko","pt","ru","es","tr","vi"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["sortie"],"lu":"https://docs.x.ai/developers/release-notes.md (« ### Text-to-Speech is available The Text-to-Speech API is now generally available. Generate natural-sounding speech from text with Grok. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.x.ai/developers/model-capabilities/audio/text-to-speech.md (« Convert text into spoken audio with a single API call. The API supports a rich set of expressive voices, inline speech tags for fine-grained delivery control, and output formats from high-fidelity MP3 to telephony-optimized μ-law. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.x.ai/developers/model-capabilities/audio/text-to-speech.md (« Clone any voice from a short reference clip with the [Custom Voices API] »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.x.ai/developers/model-capabilities/audio/text-to-speech.md (« The TTS API supports 20 languages via BCP-47 language codes. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.x.ai/developers/model-capabilities/audio/text-to-speech.md (« | French | `fr` | »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":16,"sur":31,"valeur":1149.21,"unite":"Elo","bas":1128.21,"haut":1170.21,"votes":1218,"chiffres":{"prix_par_million_caracteres":15,"date_sortie":"2026-03-16"},"voisins":["speechifyai-simba-3-0","elevenlabs-flash-v2-5"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/xai","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":27,"sur":96,"valeur":1146.3,"unite":"Elo","bas":1132.3,"haut":1160.3,"votes":1744,"chiffres":{"prix_par_million_caracteres":15,"date_sortie":"2026-03-16"},"voisins":["minimax-speech-2-8-turbo","async-flash-v1-5"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/xai","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"SpaceXAI TTS"}}