{"id":"voxtral-3","slug":"voxtral-3","name":"Voxtral 3","orgId":"mistral","family":"voxtral-3","releaseDate":null,"availability":"announced","openWeights":false,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/MistralAI/status/2112574615318876178","hfRepo":null,"modalities":["audio"],"aliases":["Voxtral 3","voxtral 3","voxtral-3","voxtral small transcribe 3","voxtral mini transcribe 3","voxtral mini transcribe realtime 3","voxtral realtime transcribe 3","voxtral mini tts 3","voxtral speech 3","voxtral 3 tts"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-20","announced":"2026-10-20","blurb":"Mistral's new speech-to-text and text-to-speech models, with a voice agent SDK built on LiveKit and Pro Voice cloning from up to 30 minutes of audio. The lab says the TTS model covers 35+ languages and 50+ dialects. Available through the Mistral API; open weights not stated.","api":"live","openWeights":"unknown","facts":[{"label":"Models","value":"Voxtral Small Transcribe 3, Voxtral Mini Transcribe 3, Voxtral Mini Transcribe Realtime 3 and Voxtral Mini TTS 3 (also called Voxtral Speech 3; Artificial Analysis lists it as Voxtral 3 TTS)"},{"label":"Size","value":"Voxtral Mini Transcribe 3 is 4B parameters (Mistral blog); other sizes not stated"},{"label":"Access","value":"Mistral API (European, US and global endpoints); the blog also mentions self-deployment"},{"label":"Weights","value":"Not stated; no Voxtral 3 repos on Hugging Face as of Oct 20, 2026","unsure":true},{"label":"Price (Mistral)","value":"Mini Transcribe 3 $0.0035/min, Small Transcribe 3 $0.0040/min, Mini Transcribe Realtime 3 $0.008/min, Speech 3 $13 per 1M characters"},{"label":"Price (Artificial Analysis)","value":"Lists Voxtral 3 TTS at $13 per 1M characters"},{"label":"Voice agent SDK","value":"Built on LiveKit: Transcribe listens, a reasoning model calls tools, Speech replies"}],"claims":["Lab claim: Voxtral Small Transcribe 3 is state-of-the-art in multilingual transcription, diarization and context-biasing.","Lab claim: Voxtral Mini TTS 3 achieves state-of-the-art expressiveness in 35+ languages and 50+ dialects.","Lab claim: Pro Voice replicates a voice from up to 30 minutes of audio across every supported language."],"sources":[{"kind":"lab","title":"Mistral AI announcement on X","url":"https://x.com/MistralAI/status/2112574615318876178","date":"2026-10-20"},{"kind":"lab","title":"Voxtral 3 (Mistral AI blog)","url":"https://mistral.ai/news/voxtral-3/","date":"2026-10-20"},{"kind":"press","title":"Artificial Analysis thread on X (pricing and its own evaluations)","url":"https://x.com/ArtificialAnlys/status/2112587905222709432","date":"2026-10-20"}],"pitch":"state-of-the-art Transcribe and Speech models powering Mistral's new voice agents API","firstBenchmark":null},"organization":{"id":"mistral","name":"Mistral","slug":"mistral","country":null,"url":null,"color":"#F2A73B","mark":"Mi"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 20, 2026; no independent results yet.","lead":"As of Oct 22, 2026, Voxtral 3 is pending benchmarks on isitsota: announced Oct 20, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}