Voxtral audio cookbook

[valdugay]

Cookbook Pull Request

Description

Adds a new cookbook notebook demonstrating Voxtral, Mistral's native audio model family. The notebook covers progressive use cases from basic transcription to structured extraction and speaker diarization — all in a single API call, without any intermediate transcription step.

Dependencies: mistralai==2.4.1, python-dotenv==1.2.2

Type of Change

• New Cookbook
  • Notebook File
    • Does it work on google colab?
  • Markdown File
• Cookbook Update
  • Code Refactoring
  • Bug Fix
• README.md Update

---

• Other (please describe):

Cookbook Checklist:

• My code is easy to read and well structured.
• I've tagged the versions of any dependency required.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• My changes generate no new warnings or errors.

---

• My changes do not concern the cookbooks.

README.md Checklist

• I've added my cookbook to the table.

---

• My changes do not concern the README file.

Additional Context

The notebook covers 6 sections:

1. Basic transcription via /v1/audio/transcriptions (voxtral-mini-latest)
2. Transcription via chat completions (voxtral-small-latest)
3. Audio Q&A — direct questions on audio, no transcription step
4. Structured extraction — JSON output from audio in a single call
5. Speaker diarization — diarize=True with speaker labels and timestamps
6. Model comparison table: Mini vs Small

A sample audio file (data/audio.mp3) is included — a ~1 min two-speaker podcast about AI and audio processing. The notebook downloads it automatically from the repo.

[valdugay]

Hey @jaccolor2 @sophiamyang, would love your feedback on this when you get a chance. Thanks!