README.md

---
title: Voxtral Studio
emoji: 🎙️
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: "6.12.0"
app_file: app.py
pinned: false
license: apache-2.0
python_version: "3.11"
tags:
  - voice-cloning
  - text-to-speech
  - automatic-speech-recognition
  - mistral
  - audio
---

# 🎙️ Voxtral Studio

> **Speech-to-Text & Text-to-Speech powered by Mistral AI's Voxtral models**

## Features

| Feature | Model | Capability |
|---|---|---|
| 🎤 Speech → Text | `voxtral-mini-latest` | 13 languages, auto-detect, noise-robust |
| 🔊 Text → Speech | `voxtral-mini-tts-2603` | Natural neural TTS, mp3/wav/flac/opus |
| 🧬 Voice Cloning | `voxtral-mini-tts-2603` | Upload a voice sample, get a reusable Voice ID |

## Setup

Add your paid Mistral API key in **Settings → Secrets** as:

```
MISTRAL_API_KEY = your-key-here
```

Get a Mistral API key at [console.mistral.ai](https://console.mistral.ai). Ensure billing is active as there is no free tier available for Voxtral TTS.