Voxtral Mini TTS

Overview

Voxtral Mini TTS is Mistral's text-to-speech model. Its 30 voices are emotion-tagged rather than merely named: the same speaker is available as en_paul_neutral, en_paul_happy, en_paul_sad, en_paul_angry, and more, so you choose the delivery at request time instead of coaxing it out of the prompt.

Usage

All media models use the async job queue. Submit a job, then poll for the result.

Step 1: Submit Job

const res = await fetch('https://api.yepapi.com/v1/media/queue', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'mistralai/voxtral-mini-tts',
    prompt: 'Your text to speak goes here.',
    options: { voice: 'en_paul_neutral' },
  }),
});
const { data } = await res.json();
// data.jobId — use this to poll for results

curl -X POST https://api.yepapi.com/v1/media/queue \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/voxtral-mini-tts", "prompt": "Your text to speak goes here."}'

Step 2: Poll for Result

const status = await fetch(`https://api.yepapi.com/v1/media/status/${data.jobId}`, {
  headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status — "pending" | "processing" | "completed" | "failed"
// job.result.audio — { mimeType, base64 } when completed

curl https://api.yepapi.com/v1/media/status/JOB_ID \
  -H "x-api-key: YOUR_API_KEY"

Write the audio to a file:

import { writeFileSync } from 'node:fs';

writeFileSync('speech.mp3', Buffer.from(job.result.audio.base64, 'base64'));

Request Body

Voices

en_paul_neutral is used when options.voice is omitted. 30 voices available (10 of 30 shown):

• en_paul_neutral
• en_paul_happy
• en_paul_sad
• en_paul_angry
• en_paul_excited
• gb_oliver_neutral
• gb_oliver_curious
• gb_jane_sarcasm
• gb_jane_confused
• fr_marie_neutral

Features

• 30 emotion-tagged voices (neutral, happy, sad, angry, excited, curious, sarcastic…)
• Three speakers across US English, UK English, and French
• Fastest model in our timing tests (~1.8s for a short line)
• Delivery selected by voice ID, not prompt engineering

Billing

Speech is billed on the length of the input text, in UTF-8 bytes — for English text one byte is one character. The cost is known before synthesis starts, so the balance check at submit time quotes the exact final charge. Jobs have a $0.01 minimum.