by MistralReleased 19 April 2026
Voxtral Mini TTS turns text into natural-sounding speech and returns audio. It can clone a voice without extra training, and it comes with 30 preset voices from four speakers in English, British English and French, each in moods such as cheerful, sad or angry. Input is limited to about 4 pages of text per request.
You pay for what each request uses. No subscription, no minimum.
One paragraph read aloud, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Characters | 5 857,91 DA |
per 1M characters
One company runs this model. OpenDunes sends every request to it. DA per 1M characters: ↑ what you send.
| Provider | ↑ Sent | Latency | Uptime |
|---|---|---|---|
| Mistral · Zdr | 5 325,37 | … | … |
| MistralEurope | 5 857,91 | … | … |
You pay the price of the provider that served your request. Prices read 15:20 · speed over the last 30 minutes · uptime over 3 days.
Swap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
with client.audio.speech.with_streaming_response.create(
model="mistralai/voxtral-mini-tts-2603",
input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
voice="en_paul_sad",
) as resp:
resp.stream_to_file("speech.mp3")Runs this request once on your balance.
About 3,51 DA per paragraph read aloud. ↑ 5 857,91 DA per 1M characters.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Voxtral Mini TTS turns text into natural-sounding speech and returns audio. It can clone a voice without extra training, and it comes with 30 preset voices from four speakers in English, British English and French, each in moods such as cheerful, sad or angry. Input is limited to about 4 pages of text per request.
Voxtral TTS 3 costs 0,65 DA less for the same paragraph read aloud.
Deposit dinars with your Edahabia or CIB card. Every model, Voxtral Mini TTS included, is paid from that balance. No foreign card, no conversion.
Mistral names English, French, Spanish, German, Italian, Portuguese, Dutch, Arabic and Hindi. Darja is not named.
30 voices. Cloning from a sample: not stated.
Mistral. Released 19 April 2026.
Mistral's flagship speech-to-text model that turns audio into transcripts with word timestamps and speaker labels, with context biasing for domain-specific vocabulary
The Voxtral Mini derivative that only transcribes, taking audio from meetings, voice notes and podcasts and returning the text through a standard transcription request
Mistral's compact speech-to-text model that turns audio into transcripts with word timestamps and speaker labels, and can be steered with context biasing to catch domain terms
Mistral AI's text embedding model from late 2023, whose 1024-dimension vectors capture how passages relate, for semantic search and RAG; Codestral Embed is the version for code
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Clones a voice No.
30 voices
Speak the replies of a phone agent with little delay
Copy a brand voice from a short recording
Read app messages aloud in Arabic or French