{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:04:33.454Z","data":{"recordId":"wsa_28bsug4i5nbx","score":0.95,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://mistral.ai/news/voxtral-tts/","publisher":"Mistral","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-29T00:08:40.326Z","detectedPublishedAt":"2026-03-23T16:00:00.000Z","rights":"original"}],"claims":[{"id":"77c2d5e4-2e02-4de2-9810-84ba8ec65346","kind":"capability","statement":"Voxtral TTS supports speech generation in English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"It supports state-of-the-art performance in 9 languages: English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic.","rights":"original"}}]},{"id":"904ddde3-b37e-4e68-81a6-4ceae9d68ef4","kind":"capability","statement":"The model can adapt to a custom voice using a reference as little as 3 seconds.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"The model was trained to adapt to a custom voice with a reference as little as 3s and capture not just the voice but also nuances like subtle accent, inflections, intonations and even disfluencies similar to those expressed in the reference.","rights":"original"}}]},{"id":"cc16d2ab-dd8e-48bd-bcc7-ad4e0aac4b16","kind":"capability","statement":"The model natively generates up to two minutes of audio, while the API handles arbitrarily long generations.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"The model natively generates up to two minutes of audio, and our API handles arbitrarily long generations with smart interleaving.","rights":"original"}}]},{"id":"ebed7809-1d1e-49c5-a1bb-6c9403b64207","kind":"availability","statement":"Voxtral TTS is available now via API and can be tested in Mistral Studio and Le Chat.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"Available via API and Mistral Studio, it offers cost-effective, high-quality voice generation starting at $0.016 per 1k characters.","rights":"original"}}]},{"id":"80bba6ff-ec28-4420-b5d8-5def681940e9","kind":"pricing","statement":"API pricing starts at $0.016 per 1k characters.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"Available via API and Mistral Studio, it offers cost-effective, high-quality voice generation starting at $0.016 per 1k characters.","rights":"original"}}]},{"id":"fb3524f0-233a-49ab-9b7a-417dcf670c63","kind":"availability","statement":"A model with several reference voices is available as open weights on Hugging Face under CC BY-NC 4.0.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"A model with several reference voices is available as open weights on Hugging Face under CC BY NC 4.0 license.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}