Voxtral Mini Transcribe 2
Transcription by Mistral
MistralReady to build with Voxtral Mini Transcribe 2?
Get Started FreeParameters & options
Label each passage with its speaker, and switch the transcript to a timestamped, speaker-labelled format.
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Names, products and terms the audio contains, so the model spells them right.
Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.
Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.
Explore similar models
MistralVoxtral Small 24B
MistralVoxtral Mini 3B
Voxtral Mini 3B is a 3-billion-parameter open-source speech-to-text model released by Mistral in July 2025.
MistralMistral OCR 4.1
GoogleGemini 3.5 Transcribe
ElevenLabsScribe v2
Scribe v2 is a speech-to-text transcription model from ElevenLabs that supports speaker identification.
OpenAIGPT Transcribe
GPT Transcribe is a speech-to-text model from OpenAI, released in March 2025, that converts spoken audio into written text.
Start building with Voxtral Mini Transcribe 2
No API keys required. Create AI-powered workflows with Voxtral Mini Transcribe 2 in minutes — free.