How do I use Universal-3.5 Pro 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 Universal-3.5 Pro?

Hormouz serves Universal-3.5 Pro 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. Send WAV audio only. Code written for OpenAI's SDK works by changing only the base URL.

Which audio formats does Universal-3.5 Pro accept?

WAV only. Convert other formats such as mp3 or m4a to WAV before sending, for example with ffmpeg.

AssemblyAI: Universal-3.5 Pro: audio model

Universal-3.5 Pro is AssemblyAI's speech-to-text model, returning a complete transcript with word-level timestamps in one response. Reachable from inside Iran through Hormouz.

Pricing:: $0.0075/minute of audio
Type:: audio

Audio

Universal-3.5 Pro is a speech-to-text model from AssemblyAI. It returns a complete transcript with word-level timestamps in a single synchronous response, which suits short clips that need an answer straight away.

Hormouz serves Universal-3.5 Pro 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. It accepts WAV audio only. On Persian speech our tests gave a fair result; for the best Persian accuracy, compare it with Scribe v2 or MAI-Transcribe 2.

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.

Universal-3.5 Pro is AssemblyAI's speech-to-text model served through its Sync API, returning a complete transcript with word-level timestamps in a single synchronous response for audio clips up to 120 seconds....

Quickstart

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=assemblyai/universal-3-5-pro \
  -F file=@audio.mp3

Specs

Vendor	Assemblyai
Type	Audio
Context window	—
Pricing	$0.0075/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=assemblyai/universal-3-5-pro \
  -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="assemblyai/universal-3-5-pro", 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: "assemblyai/universal-3-5-pro",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the AssemblyAI: Universal-3.5 Pro API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches AssemblyAI: Universal-3.5 Pro 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 Universal-3.5 Pro 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 Universal-3.5 Pro 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 Universal-3.5 Pro?: Hormouz serves Universal-3.5 Pro 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. Send WAV audio only. Code written for OpenAI's SDK works by changing only the base URL.
Which audio formats does Universal-3.5 Pro accept?: WAV only. Convert other formats such as mp3 or m4a to WAV before sending, for example with ffmpeg.

Updated 2026-10-13