{"id":"inworld-realtime-tts-2-flash","nom":"Realtime TTS-2 Flash","editeur":"Inworld AI","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://docs.inworld.ai/tts/tts-models","essayer":"https://platform.inworld.ai/tts"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/inworld-realtime-tts-2-flash/","releve":"2026-10-19","en_bref":"14e sur 31 en synthèse vocale en français, dans un groupe de 5 modèles trop proches pour être départagés ; 12e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 6 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Variante rapide et économique de Realtime TTS-2 d'Inworld, avec un premier octet audio en 20 ms (P90 côté serveur), cinq fois moins que TTS-2. Elle couvre les mêmes langues et le clonage instantané, mais sans les instructions de direction ni le clonage professionnel.","sortie":"2026-08-09","langues":{"annoncees":{"annoncees":"470 langues (623 codes de langue et de région), dont le français","nombre":470,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation","sortie"],"lu":"https://docs.inworld.ai/release-notes/tts.md (« Launched Realtime TTS-2 Flash (`inworld-tts-2-flash`), the fastest member of the TTS-2 family »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.inworld.ai/release-notes/tts.md (« Steering](https://docs.inworld.ai/tts/capabilities/steering.md) instructions and [Professional Voice Cloning](https://docs.inworld.ai/tts/professional-voice-cloning.md) are supported on `inworld-tts-2` only »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.inworld.ai/tts/tts-models.md (« Our lowest latency - 20 ms TTFB »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.inworld.ai/release-notes/tts.md (« 20 ms time to first audio (server-side P90 TTFB, excluding network latency) - 5× faster than `inworld-tts-2` at 100 ms »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.inworld.ai/tts/capabilities/multilingual.md (« The Realtime TTS-2 models - `inworld-tts-2` and `inworld-tts-2-flash` - share the same language support. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.inworld.ai/tts/capabilities/multilingual.md (« | French | `fr` | `fr-FR` | »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":14,"sur":31,"valeur":1155.17,"unite":"Elo","bas":1134.17,"haut":1176.17,"votes":1078,"chiffres":{"prix_par_million_caracteres":10.42,"date_sortie":"2026-08-25"},"voisins":["elevenlabs-multilingual-v2","speechifyai-simba-3-0"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/inworld","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":12,"sur":96,"valeur":1218.99,"unite":"Elo","bas":1205.99,"haut":1231.99,"votes":2459,"chiffres":{"prix_par_million_caracteres":10.42,"date_sortie":"2026-08-25"},"voisins":["breeze-tts-2","vui-labs-luna-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/inworld","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Realtime TTS-2 Flash"}}