Voxtral Mini TTS API
Voxtral Mini TTS text to speech — 30 emotion-tagged voices, billed on input length.
Mistral's speech model with 30 emotion-tagged voices. The same speaker ships as neutral, happy, sad, angry, excited, curious, and sarcastic variants — you pick the delivery by voice ID instead of prompting for it.
Takes 30 seconds.
Voxtral Mini TTS API pricing
Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated October 23, 2026.
| Billing | Price |
|---|---|
| Rate | $0.0338/1K chars |
| What it costs | Per job |
|---|---|
| Short reply200 characters | $0.0068 |
| Blog post narration10,000 characters (~1,600 words) | $0.338 |
| Audiobook chapter100,000 characters | $3.38 |
4,900+
Developers
2.3M+
API calls served
184
Endpoints
$0.01
Per call
Yep, that's it.
Playground coming soon — use the API endpoint directly with your API key.
Voxtral Mini TTS specs
| Provider | Mistral |
|---|---|
| Model ID | mistralai/voxtral-mini-tts |
| Endpoint | /v1/media/queue |
| Type | Text to Speech |
| Output formats | mp3 |
| Voices | 12 presets (default en_paul_neutral) |
How to get a Voxtral Mini TTS API key
- 1
Create an account
Sign up at yepapi.com with Google or email. It takes about 30 seconds.
- 2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
- 3
Call Voxtral Mini TTS
Send a request to /v1/media/queue with the x-api-key header and model "mistralai/voxtral-mini-tts".
- 4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.
Strengths
Thirty voices are emotion-tagged, so `en_paul_angry` and `en_paul_happy` are the same speaker with different delivery — no prompt engineering required.
Returned a short line in about 1.8 seconds, the quickest of the speech models we timed.
US English, UK English, and French speakers, each with their own emotional range.
Because delivery is a parameter rather than a prompt, the same input reliably produces the same read.
Quick start
Copy this snippet and start making calls with Voxtral Mini TTS.
// Step 1: Submit job
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "mistralai/voxtral-mini-tts",
"prompt": "You did what? No — start from the beginning, and this time don't leave out the part about the fire alarm.",
"options": {
"voice": "en_paul_neutral"
}
}),
});
const { data } = await res.json();
const jobId = data.jobId;
// Step 2: Poll for result
const status = await fetch(`https://api.yepapi.com/v1/media/status/${jobId}`, {
headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status: "pending" | "processing" | "completed" | "failed"
// job.result: { text?, image?, audio?, video? }Voxtral Mini TTS vs similar models
Every model below runs on the same API key — switch by changing the model ID.
| Model | Provider | Price |
|---|---|---|
| Voxtral Mini TTS | Mistral | $0.0338/1K chars |
| Voxtral TTS 3 | Mistral | $0.0302/1K chars |
| Kokoro 82M | hexgrad | $0.0014/1K chars |
| Fish Audio Drama 3 | Fish Audio | $0.0042/1K chars |
| HeyGen Voice Turbo | HeyGen | $0.0084/1K chars |
| Sesame CSM 1B | Sesame | $0.0148/1K chars |
| MAI-Voice-2.1 Flash | Microsoft | $0.0316/1K chars |
| HeyGen Voice | HeyGen | $0.0316/1K chars |
Why use Voxtral Mini TTS through YepAPI?
Voxtral Mini TTS API — emotion-tagged speech from Mistral
Voxtral Mini TTS is Mistral's text-to-speech model, and its distinguishing feature is that emotion is a voice ID rather than a prompt. The same speaker is available as neutral, happy, sad, angry, excited, confident, curious, and sarcastic variants across 30 voices.
That makes delivery reproducible: pick `en_paul_confident` and you get the same read every time. On YepAPI it costs $0.0338 per 1,000 characters through the media queue.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
Mistral's speech model with 30 emotion-tagged voices. The same speaker ships as neutral, happy, sad, angry, excited, curious, and sarcastic variants — you pick the delivery by voice ID instead of prompting for it.
Voxtral Mini TTS costs $0.0338/1K chars through YepAPI, billed per request with no monthly fee. For example, a short reply (200 characters) costs about $0.0068.
Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for Voxtral Mini TTS and every other model — no separate Mistral account or waitlist.
Use "mistralai/voxtral-mini-tts" as the model on /v1/media/queue. The short alias "voxtral" also works.
Explore more models
Voxtral TTS 3
MistralVoxtral TTS 3 text to speech — 66 preset voices with emotion and pace tags, billed on input length.
MiniMax Speech 2.8 Turbo
MiniMaxMiniMax Speech 2.8 Turbo text to speech — fast, flexible-voice speech, billed on input length.
HeyGen Voice Turbo
HeyGenHeyGen Voice Turbo text to speech — lower-latency HeyGen Voice with the same 10 voices, billed on input length.
Fish Audio S2.1 Pro Free
Fish AudioFish Audio S2.1 Pro Free text to speech — free tier for prototyping, billed on input length.
MAI-Voice-2
MicrosoftMAI-Voice-2 text to speech — expressive speech in 15 languages, billed on input length.
Gemini 3.1 Flash TTS
GoogleGemini 3.1 Flash TTS text to speech — 70+ languages, 200+ audio tags, billed on input length.
More Text to Speech models
- Qwen-Audio 3.0 TTS Plus API · Qwen
- Eleven v4 Turbo API · ElevenLabs
- Eleven Turbo v2.5 API · ElevenLabs
- Eleven Multilingual v2 API · ElevenLabs
- Sesame CSM 1B API · Sesame
- Deepgram Flux TTS API · Deepgram
- Grok Voice TTS 1.0 API · xAI
- HeyGen Voice API · HeyGen
- Eleven v3 Conversational API · ElevenLabs
- Deepgram Aura-2 API · Deepgram
- MAI-Voice-2.1 API · Microsoft
- Eleven Turbo v2 API · ElevenLabs