How do I use Voxtral Mini 3B 2507 from inside Iran?

Create a Hormouz account and generate an API key. Hormouz gives you a stable route to the model from inside Iran, with no foreign credit card or circumvention tooling needed.

How do I call Voxtral Mini 3B 2507?

Hormouz serves Voxtral Mini 3B 2507 on two endpoints. The OpenAI-compatible POST /v1/audio/transcriptions takes the file as the multipart field "file", or as JSON input_audio with base64 data and format, and returns {text, usage} in the same response. POST /v1/predictions handles long recordings in the background: input.audio is an https URL or a data: URI, input.language is optional. Code written for OpenAI's SDK works by changing only the base URL.

Mistral: Voxtral Mini 3B 2507: audio model

Voxtral Mini 3B 2507 is Mistral's compact speech and audio understanding model, for transcription and translation. Reachable from inside Iran through Hormouz.

Pricing:: $0.001/minute of audio
Type:: audio

Audio

Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It suits transcription, translation and compact audio processing workloads.

Hormouz serves Voxtral Mini 3B 2507 on two endpoints: the OpenAI-compatible /v1/audio/transcriptions, which returns the text in the same response, and /v1/predictions for long recordings processed in the background. In our tests Persian speech came back romanised, in Latin letters rather than Persian script. For Persian, choose a model that did well in our tests, such as Scribe v2, MAI-Transcribe 2 or Whisper Large V3.

Billing is per minute of audio; the current rate is in the price table on this page, and you pay only for what you use. Hormouz provides stable access to it from inside Iran, with no foreign credit card or circumvention tooling required.

Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.

Quickstart

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=mistralai/voxtral-mini-3b-2507 \
  -F file=@audio.mp3

Specs

Vendor	Mistral AI
Type	Audio
Context window	—
Pricing	$0.001/minute of audio
API	transcriptions

Code example

cURL

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=mistralai/voxtral-mini-3b-2507 \
  -F file=@audio.mp3

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
with open("audio.mp3", "rb") as f:
    tr = client.audio.transcriptions.create(model="mistralai/voxtral-mini-3b-2507", file=f)
print(tr.text)

JavaScript

import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const tr = await client.audio.transcriptions.create({
  model: "mistralai/voxtral-mini-3b-2507",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the Mistral: Voxtral Mini 3B 2507 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Mistral: Voxtral Mini 3B 2507 and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Voxtral Mini 3B 2507 cost?: Billing is per minute of audio; the current rate is in the price table on this page, and you pay only for what you use.
How do I use Voxtral Mini 3B 2507 from inside Iran?: Create a Hormouz account and generate an API key. Hormouz gives you a stable route to the model from inside Iran, with no foreign credit card or circumvention tooling needed.
How do I call Voxtral Mini 3B 2507?: Hormouz serves Voxtral Mini 3B 2507 on two endpoints. The OpenAI-compatible POST /v1/audio/transcriptions takes the file as the multipart field "file", or as JSON input_audio with base64 data and format, and returns {text, usage} in the same response. POST /v1/predictions handles long recordings in the background: input.audio is an https URL or a data: URI, input.language is optional. Code written for OpenAI's SDK works by changing only the base URL.
Does Voxtral Mini 3B support Persian?: Not well. In our tests Persian speech came back romanised, in Latin letters rather than Persian script. For Persian, choose a model that did well in our tests, such as Scribe v2, MAI-Transcribe 2 or Whisper Large V3.

Updated 2026-10-13