How do I use Qwen3 ASR 1.7B 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 Qwen3 ASR 1.7B?

Hormouz serves Qwen3 ASR 1.7B 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.

Qwen3 ASR 1.7B or Qwen3 ASR 0.6B?

For Persian, choose 1.7B: in our tests it gave an accurate Persian transcript, while the smaller 0.6B was only fair. The 0.6B model suits languages where its accuracy is enough and a lower cost matters more.

Qwen: Qwen3 ASR 1.7B: audio model

Qwen3 ASR 1.7B is Qwen's speech recognition model for 30 languages and 22 Chinese dialects, with language identification. Reachable from inside Iran through Hormouz.

Pricing:: $0.00045/minute of audio
Type:: audio

Audio

Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen (Alibaba). It identifies the spoken language and transcribes across 30 languages and 22 Chinese dialects.

Hormouz serves Qwen3 ASR 1.7B 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.

Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference...

Quickstart

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=qwen/qwen3-asr-1.7b \
  -F file=@audio.mp3

Specs

Vendor	Qwen
Type	Audio
Context window	—
Pricing	$0.00045/minute of audio
API	transcriptions

Sizes in this family

Size	Context window	Pricing
0.6B	—	$0.0001998/minute of audio
1.7B	—	$0.00045/minute of audio

Code example

cURL

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=qwen/qwen3-asr-1.7b \
  -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="qwen/qwen3-asr-1.7b", 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: "qwen/qwen3-asr-1.7b",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the Qwen: Qwen3 ASR 1.7B API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Qwen: Qwen3 ASR 1.7B 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 Qwen3 ASR 1.7B 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 Qwen3 ASR 1.7B 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 Qwen3 ASR 1.7B?: Hormouz serves Qwen3 ASR 1.7B 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.
Qwen3 ASR 1.7B or Qwen3 ASR 0.6B?: For Persian, choose 1.7B: in our tests it gave an accurate Persian transcript, while the smaller 0.6B was only fair. The 0.6B model suits languages where its accuracy is enough and a lower cost matters more.

Updated 2026-10-13