Voxtral TTS 3

Speech

voxtral-mini-tts-3-0

MistralAI|Created Oct 30, 2026

Speech

Our state-of-the-art text-to-speech model with zero-shot voice cloning and professional voice cloning. Supports 35+ languages and 50+ dialects, streaming with ~90 ms time-to-first-audio, 5 output formats, 34 emotion tags, and 2 pace tags.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI
from pathlib import Path

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

speech_file_path = Path("speech.mp3")
resp = client.audio.speech.create(
    model="voxtral-mini-tts-3-0",
    voice="alloy",
    input="Hello from NagaAI Text-to-Speech!"
)
resp.stream_to_file(speech_file_path)