Quickstart: transcribe an audio file

This tutorial will show you how to transcribe audio from a file. To transcribe prerecorded audio from other sources, see File transcription. To transcribe streaming audio in real time, see the realtime quickstart.

First, you'll need a Mistral API key. If you don't have one, then go to Studio. Navigate to the API keys section and create a new API key.

Store your API key in the MISTRAL_API_KEY environment variable:

export MISTRAL_API_KEY="your-api-key"

export MISTRAL_API_KEY="your-api-key"

To use Python or TypeScript, install the Mistral SDK. The curl example needs no install.

pip install mistralai

pip install mistralai

To follow along without a file of your own, download the sample recording:

curl -O https://docs.mistral.ai/audio/obama.mp3

curl -O https://docs.mistral.ai/audio/obama.mp3

Use this code to transcribe speech from an audio file to text. The speech can be in multiple languages.

import os

from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

with open("obama.mp3", "rb") as audio:
    transcription = client.audio.transcriptions.complete(
        model="voxtral-mini-transcribe-3",
        file={"file_name": "obama.mp3", "content": audio},
    )

print(transcription.text)

import os

from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

with open("obama.mp3", "rb") as audio:
    transcription = client.audio.transcriptions.complete(
        model="voxtral-mini-transcribe-3",
        file={"file_name": "obama.mp3", "content": audio},
    )

print(transcription.text)

I'm recording some speech now for testing. Et on peut aussi parler français !

I'm recording some speech now for testing. Et on peut aussi parler français !