Shenava v3: image generation model
Shenava v3 is a Persian-first speech-to-text model at a light price. Reachable from inside Iran through Hormouz.
- Pricing:
- $0.00332 / minute of audio
- Type:
- audio
- Audio
Shenava v3 is the lower-price tier of Arpanet's Persian-first speech recognition. Send an audio or video file (mp3, wav, ogg, m4a, webm, mp4 or mov) and it returns the transcript, a version labelled by speaker and the language it detected. Shenava v4 is the higher-accuracy tier.
It is billed per minute of input audio, at the rate shown on this page. Through Hormouz you send the file as a link or data URI to POST /v1/predictions and read the transcript from the result.
Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Persian-first speech-to-text, light-price tier. Send an audio or video file (mp3, wav, ogg, m4a, webm, mp4, mov) as input.audio (https URL or data: URI); returns the transcript, a speaker-labelled transcript and the detected language. Billed per minute of input audio.
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":"arpanet/shenava-v3","input":{"audio":"https://example.com/input.mp3"}}'Specs
| Vendor | Arpanet |
|---|---|
| Type | Audio |
| Context window | — |
| Pricing | $0.00332 / minute of audio |
| API | predictions |
Code example
# Create the prediction, then poll until succeeded
curl -s https://api.hormouz.net/v1/predictions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"version":"arpanet/shenava-v3","input":{"audio":"https://example.com/input.mp3"}}'import requests
BASE = "https://api.hormouz.net/v1"
H = {"Authorization": "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json"}
r = requests.post(f"{BASE}/predictions", headers=H,
json={"version": "arpanet/shenava-v3", "input": {"audio":"https://example.com/input.mp3"}})
print(r.json()["id"])const BASE = "https://api.hormouz.net/v1";
const res = await fetch(`${BASE}/predictions`, {
method: "POST",
headers: { Authorization: "Bearer ng-YOUR_API_KEY", "Content-Type": "application/json" },
body: JSON.stringify({ version: "arpanet/shenava-v3", input: {"audio":"https://example.com/input.mp3"} }),
});
const { id } = await res.json();Buy the Shenava v3 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Shenava v3 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
- What is Shenava v3 good for?
- Transcribing Persian meetings, interviews, lectures, voice messages and videos at a low price.
- Shenava v3 or v4?
- v3 is cheaper; v4 is more accurate. Use v4 when transcript quality matters most.
- How do I access Shenava v3 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Updated 2026-10-13