How do I use CSM 1B 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.

What is the difference between the conversational and read-speech voices of CSM 1B?

The conversational voices sound like someone talking in a dialogue; the read-speech voices sound like someone reading a text aloud.

Sesame: CSM 1B: audio model

CSM 1B is Sesame's conversational speech model, producing English speech in conversational and read-speech styles. Reachable from inside Iran through Hormouz.

Pricing:: $7/M characters
Type:: audio

Audio

CSM 1B is a conversational speech model from Sesame. It takes text and produces English speech, with voices in conversational and read-speech styles.

At 1 billion parameters it is a compact model for dialogue-oriented applications such as voice assistants and interactive agents. Hormouz serves CSM 1B 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 "conversational_a", 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.

CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it...

Quickstart

curl https://api.hormouz.net/v1/audio/speech \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sesame/csm-1b","voice":"conversational_a","input":"Hello from Hormouz.","response_format":"mp3"}' \
  --output speech.mp3

Specs

Vendor	Sesame
Type	Audio
Context window	—
Pricing	$7/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":"sesame/csm-1b","voice":"conversational_a","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="sesame/csm-1b",
    voice="conversational_a",
    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: "sesame/csm-1b",
  voice: "conversational_a",
  input: "Hello from Hormouz.",
  response_format: "mp3",
});
await writeFile("speech.mp3", Buffer.from(await speech.arrayBuffer()));

Buy the Sesame: CSM 1B API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Sesame: CSM 1B 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 CSM 1B 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 CSM 1B 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 CSM 1B?: Hormouz serves CSM 1B 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 "conversational_a", and response_format to mp3 or pcm.
What is the difference between the conversational and read-speech voices of CSM 1B?: The conversational voices sound like someone talking in a dialogue; the read-speech voices sound like someone reading a text aloud.

Updated 2026-10-13