How do I use Chirp 3 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 Chirp 3?

Hormouz serves Chirp 3 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. Each request takes at most 60 seconds of audio. Code written for OpenAI's SDK works by changing only the base URL.

Is there a length limit for Chirp 3?

Yes. Each request takes at most 60 seconds of audio, and longer audio is refused. Split longer recordings into parts of up to 60 seconds, or use a model without this limit, such as Scribe v2 or Whisper Large V3.

Google: Chirp 3: audio model

Chirp 3 is Google's multilingual speech-to-text model, with automatic language detection and punctuation. Reachable from inside Iran through Hormouz.

Pricing:: $0.016/minute of audio
Type:: audio

Audio

Chirp 3 is Google's multilingual speech-to-text model. Google lists 24 generally available languages and more than 77 in preview, with automatic language detection and automatic punctuation.

Hormouz serves Chirp 3 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. Each request takes at most 60 seconds of audio; longer audio is refused.

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.

Chirp 3 is Google's latest multilingual speech-to-text model. It offers enhanced transcription accuracy across 24 GA languages and 77+ preview languages, with support for automatic language detection, automatic punctuation, and...

Quickstart

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

Specs

Vendor	Google
Type	Audio
Context window	—
Pricing	$0.016/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=google/chirp-3 \
  -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="google/chirp-3", 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: "google/chirp-3",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the Google: Chirp 3 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Google: Chirp 3 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 Buy Gemini API access, paid in rial

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 Chirp 3 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 Chirp 3 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 Chirp 3?: Hormouz serves Chirp 3 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. Each request takes at most 60 seconds of audio. Code written for OpenAI's SDK works by changing only the base URL.
Is there a length limit for Chirp 3?: Yes. Each request takes at most 60 seconds of audio, and longer audio is refused. Split longer recordings into parts of up to 60 seconds, or use a model without this limit, such as Scribe v2 or Whisper Large V3.

Updated 2026-10-13