How do I use Scribe v2 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 Scribe v2?

Hormouz serves Scribe v2 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, and input.diarize set to true labels the speakers. Code written for OpenAI's SDK works by changing only the base URL.

Can Scribe v2 tell speakers apart?

Yes. On /v1/predictions set input.diarize to true; on /v1/audio/transcriptions send diarize with response_format set to verbose_json. The transcript then comes back with each speaker's turns labelled.

ElevenLabs: Scribe v2: audio model

Scribe v2 is ElevenLabs' speech-to-text model for 90+ languages, with word-level timestamps and optional speaker labels. Reachable from inside Iran through Hormouz.

Pricing:: $0.001833/minute of audio
Discount:: −50%
Type:: audio

Audio

Scribe v2 is a speech-to-text model from ElevenLabs that transcribes audio in more than 90 languages. It returns word-level timestamps, can label who is speaking, and tags audio events in the recording.

Hormouz serves Scribe v2 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 on Persian speech it produced an accurate transcript. It suits interviews, meetings and any recording with more than one speaker.

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.

ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging.

Quickstart

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=elevenlabs/scribe-v2 \
  -F file=@audio.mp3

Specs

Vendor	Elevenlabs
Type	Audio
Context window	—
Pricing	Previous price: $0.003667/minute of audioDiscounted price: $0.001833/minute of audio−50%
API	transcriptions

Code example

cURL

curl https://api.hormouz.net/v1/audio/transcriptions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -F model=elevenlabs/scribe-v2 \
  -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="elevenlabs/scribe-v2", 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: "elevenlabs/scribe-v2",
  file: fs.createReadStream("audio.mp3"),
});
console.log(tr.text);

Buy the ElevenLabs: Scribe v2 API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches ElevenLabs: Scribe v2 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 Scribe v2 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 Scribe v2 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 Scribe v2?: Hormouz serves Scribe v2 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, and input.diarize set to true labels the speakers. Code written for OpenAI's SDK works by changing only the base URL.
Can Scribe v2 tell speakers apart?: Yes. On /v1/predictions set input.diarize to true; on /v1/audio/transcriptions send diarize with response_format set to verbose_json. The transcript then comes back with each speaker's turns labelled.

Updated 2026-10-13