How do I use Kokoro 82M 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 are Kokoro 82M voices named?

Each voice id starts with a language-and-gender prefix, for example af_heart for an American English female voice, followed by the voice name.

hexgrad: Kokoro 82M: audio model

Kokoro 82M is hexgrad's lightweight open-weight text-to-speech model, with 54 voices across 8 languages at a very low cost. Reachable from inside Iran through Hormouz.

Pricing:: $4/M characters
Type:: audio

Audio

Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It speaks 8 languages: American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese and Chinese.

Its 54 preset voices are grouped by language and gender, and at 82M parameters it is one of the most cost-efficient ways to add speech to a product. Hormouz serves Kokoro 82M on two endpoints: the OpenAI-compatible /v1/audio/speech, which returns the audio in the same response, and /v1/predictions for background jobs. Set voice to one of the model's own voices, for example "af_heart", and response_format to mp3 or pcm.

Billing is per character of input text; 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.

Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...

Quickstart

curl https://api.hormouz.net/v1/audio/speech \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"hexgrad/kokoro-82m","voice":"af_alloy","input":"Hello from Hormouz.","response_format":"mp3"}' \
  --output speech.mp3

Specs

Vendor	Hexgrad
Type	Audio
Context window	—
Pricing	$4/M characters
API	speech

Code example

cURL

curl https://api.hormouz.net/v1/audio/speech \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"hexgrad/kokoro-82m","voice":"af_alloy","input":"Hello from Hormouz.","response_format":"mp3"}' \
  --output speech.mp3

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
with client.audio.speech.with_streaming_response.create(
    model="hexgrad/kokoro-82m",
    voice="af_alloy",
    input="Hello from Hormouz.",
    response_format="mp3",
) as resp:
    resp.stream_to_file("speech.mp3")

JavaScript

import OpenAI from "openai";
import { writeFile } from "node:fs/promises";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const speech = await client.audio.speech.create({
  model: "hexgrad/kokoro-82m",
  voice: "af_alloy",
  input: "Hello from Hormouz.",
  response_format: "mp3",
});
await writeFile("speech.mp3", Buffer.from(await speech.arrayBuffer()));

Buy the hexgrad: Kokoro 82M API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches hexgrad: Kokoro 82M 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 Kokoro 82M cost?: Billing is per character of input text; the current rate is in the price table on this page, and you pay only for what you use.
How do I use Kokoro 82M 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 Kokoro 82M?: Hormouz serves Kokoro 82M on two endpoints: the OpenAI-compatible /v1/audio/speech, which returns the audio in the same response, and /v1/predictions for background jobs. Set voice to one of the model's own voices, for example "af_heart", and response_format to mp3 or pcm.
How are Kokoro 82M voices named?: Each voice id starts with a language-and-gender prefix, for example af_heart for an American English female voice, followed by the voice name.

Updated 2026-10-13