How do I use Parakeet TDT 0.6B v3 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 Parakeet TDT 0.6B v3?

Hormouz serves Parakeet TDT 0.6B v3 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.

NVIDIA: Parakeet TDT 0.6B v3: audio model

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model with automatic language detection. Reachable from inside Iran through Hormouz.

Pricing:: $0.0015/minute of audio
Type:: audio

Audio

Parakeet TDT 0.6B v3 is a 600-million-parameter multilingual speech-to-text model from NVIDIA, built on the FastConformer-TDT architecture and trained on more than 670,000 hours of audio. It detects the spoken language automatically and is aimed mainly at European languages.

Hormouz serves Parakeet TDT 0.6B v3 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 Persian speech came back romanised, in Latin letters rather than Persian script. It is a better fit for European languages; for Persian, choose a model that did well in our tests, such as Scribe v2, MAI-Transcribe 2 or Whisper Large V3.

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.

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...

Quickstart

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=nvidia/parakeet-tdt-0.6b-v3 \
  -F file=@audio.mp3

Specs

Vendor	NVIDIA
Type	Audio
Context window	—
Pricing	$0.0015/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=nvidia/parakeet-tdt-0.6b-v3 \
  -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="nvidia/parakeet-tdt-0.6b-v3", 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: "nvidia/parakeet-tdt-0.6b-v3",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the NVIDIA: Parakeet TDT 0.6B v3 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches NVIDIA: Parakeet TDT 0.6B 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.

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 Parakeet TDT 0.6B v3 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 Parakeet TDT 0.6B v3 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 Parakeet TDT 0.6B v3?: Hormouz serves Parakeet TDT 0.6B v3 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.
Does Parakeet TDT 0.6B v3 support Persian?: Not well. In our tests Persian speech came back romanised, in Latin letters rather than Persian script. It is a better fit for European languages. For Persian, choose a model that did well in our tests, such as Scribe v2, MAI-Transcribe 2 or Whisper Large V3.

Updated 2026-10-13