whisper: image generation model
Whisper is an OpenAI speech-to-text model for multilingual transcription and translation, callable with a drop-in OpenAI transcriptions API, via Hormouz.
- Pricing:
- ~$0.000575 / sec (Nvidia A40 GPU)
- Type:
- audio, text
- Audio
Whisper is OpenAI's open-source speech-recognition model for multilingual transcription and translation. Whisper is OpenAI's open-source automatic speech-recognition model, offering both transcription and translation. It supports 99+ languages, accepts common formats such as mp3, mp4, wav, webm, flac and ogg, and is well-suited to noise-robust, multilingual transcription with word- and segment-level timestamps.
Whisper is served through Hormouz behind an OpenAI-compatible transcriptions API: upload an audio file and receive the transcript as JSON. Point your base URL at Hormouz and use a Hormouz key to call it from your existing code.
Pricing is usage-based at $0.0015 per minute of audio. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Quickstart
# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"version":"openai/whisper","input":{"audio":"https://example.com/input.mp3"}}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Audio, Text |
| Context window | — |
| Pricing | ~$0.000575 / sec (Nvidia A40 GPU) |
| API | predictions |
Code example
# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"version":"openai/whisper","input":{"audio":"https://example.com/input.mp3"}}'import requests
BASE = "https://api.hormouz.net/v1"
H = {"Authorization": "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json"}
r = requests.post(f"{BASE}/predictions", headers=H,
json={"version": "openai/whisper", "input": {"audio":"https://example.com/input.mp3"}})
print(r.json()["id"])const BASE = "https://api.hormouz.net/v1";
const res = await fetch(`${BASE}/predictions`, {
method: "POST",
headers: { Authorization: "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json" },
body: JSON.stringify({ version: "openai/whisper", input: {"audio":"https://example.com/input.mp3"} }),
});
const { id } = await res.json();Buy the whisper API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches whisper 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.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Whisper cost?
- Billing is usage-based at $0.0015 per minute of audio. There is no fixed monthly fee. You pay only for what you use, and current rates are shown in the Hormouz dashboard.
- How do I access Whisper from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Whisper from inside Iran, with no foreign credit card or circumvention tooling required.
- How do I call Whisper?
- Use the OpenAI-compatible transcriptions endpoint: upload an audio file (mp3, wav, m4a and other common formats) and receive the transcript back. Point your base URL at Hormouz and use a Hormouz key. Existing OpenAI SDK transcription code works unchanged.
- What languages does Whisper support?
- Whisper supports 99+ languages for transcription and can also translate speech into English, making it a fit for multilingual audio.
- What is Whisper good for?
- Whisper works well for transcribing meetings, calls, podcasts and voice notes, and translating speech across 99+ languages.
Updated 2026-10-13