How do I use GPT-4o mini TTS 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.

Can I control how it speaks?

Yes. Send an instructions field with the tone, pace or emotion you want. It has thirteen voices: alloy, ash, ballad, cedar, coral, echo, fable, marin, nova, onyx, sage, shimmer and verse.

OpenAI: GPT-4o mini TTS: audio model

GPT-4o mini TTS is OpenAI's steerable text-to-speech model: you describe how it should speak, from tone and pace to emotion. Reachable from inside Iran through Hormouz.

Pricing:: $0.6/M text tokens · $12/M audio tokens
Type:: audio

Audio

GPT-4o mini TTS is a text-to-speech model from OpenAI built on GPT-4o mini. Besides the text, it takes an instructions field that steers delivery, for example "speak calmly, like a doctor explaining a diagnosis", and offers thirteen voices.

Hormouz serves GPT-4o mini TTS 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 "coral", and response_format to mp3 or pcm. Each request takes up to 4,096 characters of text.

Billing has two parts: input text, and the length of the audio produced (OpenAI prices it in audio tokens, about 24 per second). The current rates are 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.

OpenAI's steerable text-to-speech model: tell it how to speak (tone, pace, emotion) with instructions.

Quickstart

curl https://api.hormouz.net/v1/audio/speech \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4o-mini-tts","voice":"ballad","input":"Hello from Hormouz.","response_format":"mp3"}' \
  --output speech.mp3

Specs

Vendor	OpenAI
Type	Audio
Context window	—
Pricing	$0.6/M text tokens · $12/M audio tokens
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":"openai/gpt-4o-mini-tts","voice":"ballad","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="openai/gpt-4o-mini-tts",
    voice="ballad",
    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: "openai/gpt-4o-mini-tts",
  voice: "ballad",
  input: "Hello from Hormouz.",
  response_format: "mp3",
});
await writeFile("speech.mp3", Buffer.from(await speech.arrayBuffer()));

Buy the OpenAI: GPT-4o mini TTS API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches OpenAI: GPT-4o mini TTS 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 ChatGPT (OpenAI) 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 GPT-4o mini TTS cost?: Billing has two parts: input text, and the length of the audio produced (OpenAI prices it in audio tokens, about 24 per second). The current rates are in the price table on this page, and you pay only for what you use.
How do I use GPT-4o mini TTS 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 GPT-4o mini TTS?: Hormouz serves GPT-4o mini TTS 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 "coral", and response_format to mp3 or pcm. Each request takes up to 4,096 characters of text. Code written for OpenAI's SDK works by changing only the base URL; the bare model id is accepted too.
Can I control how it speaks?: Yes. Send an instructions field with the tone, pace or emotion you want. It has thirteen voices: alloy, ash, ballad, cedar, coral, echo, fable, marin, nova, onyx, sage, shimmer and verse.

Updated 2026-10-13