Mistral AIText-to-speech

voxtral-mini-tts-3-0

JSON

Voxtral TTS 3 TTS Beta Provider default streaming, http, websocket

Mistral's Voxtral 3 text-to-speech model with zero-shot and professional voice cloning, 35+ languages, inline emotion and pace tags, and ~90 ms time-to-first-audio.

01 Price

$13.00per 1M chars

Cheaper than 80% of 95 priced text-to-speech models.

Text-to-speech $ per 1M characters, log scale 95 priced, 193 without a USD price

Text-to-speech: 95 models with a published USD price per 1M characters, from $1 to $100 and beyond, shown on a log scale.

other models this modelAll models by price

$13 per 1M input characters

Pricing source, checked 2026-11-16

02 Languages 38, 39 with regional variants

Show all 38 languages

03 Features 4 of 8 listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Get this record

curl https://voicedex.dev/v1/providers/mistral/models/voxtral-mini-tts-3-0

Free, no key needed. Use model id voxtral-mini-tts-3-0 with Mistral AI's own API. API reference.

Esc

↑↓ move↵ open