Audio

Mistral audio covers three jobs: turning speech into text, turning text into speech, and running both in live conversations. Voxtral 3 models transcribe recorded files and live streams, with speaker labels, timestamps, and custom vocabulary. They generate speech with preset or cloned voices, which you direct with emotion and pace tags. You can also send audio to a chat model to summarize or question a recording, and build voice agents that answer callers in real time.

This section is for developers who integrate audio through the API and SDKs, and for product teams who evaluate what Voxtral can do.

Every request needs an API key from AI Studio.

1. Select Create new key, give the key a name, and set an expiration date.
2. Copy the key. It appears only once.
3. Store the key in the MISTRAL_API_KEY environment variable, where the examples read it:

export MISTRAL_API_KEY="your-api-key"

export MISTRAL_API_KEY="your-api-key"

The curl examples need no installation. For Python or TypeScript, install the Mistral SDK:

pip install "mistralai[realtime]"

pip install "mistralai[realtime]"

The realtime extra adds the WebSocket client for realtime transcription.

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

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

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)

Voxtral 3 has five models: three turn speech into text, and two turn text into speech.

Voxtral Mini Transcribe 3

Transcription of recorded audio files.

Voxtral Mini Transcribe Realtime 3

Live transcription of audio streams, with configurable latency.

Voxtral Small Transcribe 3

Higher-quality transcription of recorded audio files.

Voxtral TTS 3

Speech generation from text, with preset voices and zero-shot voice cloning.

Voxtral TTS Realtime 3

Streaming speech generation for live conversations.

To choose, start from what you need to do:

To compare modes, options, and features in detail, see Speech to Text and Text to Speech.

Before you tune options or design a voice product, read how each part of the audio stack works and what each choice trades off.

Pick the scenario closest to your product. Each guide combines several capabilities into one result and links to the article behind every step.