Hormouz AIHormouzSign in

Microsoft AI: MAI-Transcribe 2: audio model

MAI-Transcribe 2 is Microsoft's multilingual speech-to-text model for 60 languages, with automatic language identification. Reachable from inside Iran through Hormouz.

Pricing:
$0.001667/minute of audio
Type:
audio
  • Audio

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI. It supports 60 languages with automatic language identification and handles code switching, where a speaker mixes languages. Microsoft reports it ranked first on the FLEURS multilingual benchmark.

Hormouz serves MAI-Transcribe 2 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 on Persian speech it produced an accurate transcript.

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.

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech,...

Quickstart

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=microsoft/mai-transcribe-2 \
  -F file=@audio.mp3

Specs

VendorMicrosoft
TypeAudio
Context window—
Pricing$0.001667/minute of audio
APItranscriptions

Code example

cURL
curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=microsoft/mai-transcribe-2 \
  -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="microsoft/mai-transcribe-2", 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: "microsoft/mai-transcribe-2",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the Microsoft AI: MAI-Transcribe 2 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Microsoft AI: MAI-Transcribe 2 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 MAI-Transcribe 2 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 MAI-Transcribe 2 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 MAI-Transcribe 2?
Hormouz serves MAI-Transcribe 2 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 MAI-Transcribe 2 support Persian?
Yes. In our tests on Persian speech it produced an accurate transcript. This is the Microsoft model to choose for Persian: the older MAI-Transcribe 1.5 does not support it.

Updated 2026-10-13