Voice and music · by Mistral AI

Voxtral Transcribe

Transcribe audio with speakers labeled and your own custom vocabulary.

speech, link → text, data · speech → text, events
Way in
Official APISign up yourself, api key
To start
$Mistral free/experiment tier (limits not checked)
Runs
In the cloudAlso through deepinfra
Checked
Nov 3, 2026Prices as of that day

What it can do 2

Transcribe audio file with diarization and segment timestamps65,536-token context shared by audio and vocab listspeech, link → text, data~$0.0035/min Mini, ~$0.004/min Small (Artificial Analysis listing; Mistral pricing page shows units only)
Transcribe live audio with turn detection80-2,400 ms configurable delayspeech → text, eventsper-minute (rate not shown on pricing page)

Does the same job

Prices and limits as of Nov 3, 2026, from Mistral AI’s own pages. They change; check before you rely on them.Not affiliated with Mistral AI. Not advice.Rankings: Artificial Analysis.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.