Voxtral Mini Transcribe V2

This is the transcription-workhorse of the Voxtral family and the model that Mistral's hosted transcription endpoint routes to by default. Use this when you want batch speech-to-text — transcribing recorded meetings, podcasts, voice notes — rather than speech understanding (Voxtral Small 24B) or real-time streaming (Voxtral Mini 4B Realtime). At $0.003 per minute of audio on Mistral's API, it's roughly half the per-minute cost of ElevenLabs Scribe while matching transcription quality according to Mistral's comparative benchmarks. Apache 2.0 for self-hostedRunning a model on hardware you control — your own servers, your own cloud instance, or your own laptop — rather than paying to access it through someone else's API. Self-hosting gives you full control over data and predictable costs, but requires the hardware and operational effort to run the model. Only possible with open-weight models. deployment.