---
title: "Voxtral Mini 3B | Micdrop"
description: "Voxtral Mini 3B tested as the transcription of a local call, more accurate than Whisper base but 35 times slower."
url: "https://micdrop.dev/docs/local-models/explorations/voxtral-stt"
---

# Voxtral Mini 3B

Tested as the transcription, instead of Whisper. It transcribes French more accurately, but it takes 35 times longer per utterance, which is too slow for a call.

Voxtral Mini transcribes, translates and answers questions about audio. There is a community ONNX export, so it runs in Node through Transformers.js, like Whisper. `examples/advanced/server/src/benchmarks/voxtral-stt.ts` runs it on French sentences spoken by Piper, with weights in `q4` on CPU:

Model

Per utterance

Word errors

Voxtral Mini 3B

~16600 ms

17 %

Whisper `base`

~470 ms

34 %

Whisper `french`

~1200 ms

11 %

Voxtral is more accurate than Whisper `base`, but 35 times slower, because it transcribes by generating tokens with a 3 billion parameter model, where Whisper runs an encoder and a small decoder. Whisper `french` is more accurate than both and takes a fourteenth of Voxtral’s time. The weights take 3 GB in `q4`. Transformers.js fails when it downloads files that large, so download them with `hf download` first.
