Platform editions
Mistral AI
Mistral cloud transcription with Voxtral Transcribe 3, live text through Voxtral Realtime, and Mistral text models for workflows.
Choose your platform
This add-on has separate macOS and Windows editions. Each page documents the features, settings, requirements, and screenshots for that platform.
macOS
v1.3.0
Voxtral Transcribe 3 with live text through Voxtral Realtime, dictionary terms, speaker labels, and Mistral text models with reasoning levels.
- Live (default): dictations with a live preview stream to Voxtral Mini Transcribe Realtime 3, and the selected transcription model writes the final text from the recording; both are billed, about $0.69 per hour with Voxtral Mini Transcribe 3
- After recording: the recording goes to the selected transcription model when you stop, at $0.21 per hour with Voxtral Mini Transcribe 3 or $0.24 with Voxtral Small Transcribe 3, without a live preview from Mistral
- In our tests the final text was there 0.3 to 0.4 seconds after the stop in Live mode, and 0.4 to 0.5 seconds with After recording
- Recordings and files always use the transcription model
Windows
v1.4.0
Voxtral Transcribe 3 and Voxtral Realtime 3 through the Mistral API, with dictionary terms, 58 languages, and Mistral text models with reasoning levels.
- Voxtral Mini Transcribe 3 as the default transcription model, Voxtral Small Transcribe 3 as the alternative
- Voxtral Mini Transcribe Realtime 3 shows live text while you speak (TypeWhisper 1.3 or newer; older versions transcribe after you stop), and the final text comes from uploading the recording to Voxtral Mini Transcribe 3, which heard dictations more accurately and was ready 0.4 to 0.6 seconds after the stop; both are billed
- Files and complete recordings with the realtime model selected upload to Voxtral Mini Transcribe 3 instead of streaming: a 63-second recording took 1 second instead of 40
- Active dictionary terms sent as context, in uploads and live sessions
