ElevenLabs: Eleven v3 Conversational: audio model
Eleven v3 Conversational is the Eleven v3 variant tuned for natural dialogue in conversational agents, across 70+ languages. Reachable from inside Iran through Hormouz.
- Pricing:
- $20/M characters
- Discount:
- −50%
- Type:
- audio
- Audio
Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimised for natural back-and-forth dialogue. It supports more than 70 languages and accepts up to 5,000 characters per request.
It is built for the turns of a conversation: short replies from support bots, voice agents and assistants that should sound like a person talking rather than reading. Hormouz serves Eleven v3 Conversational 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 "george", 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.
Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request...
Quickstart
curl https://api.hormouz.net/v1/audio/speech \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"elevenlabs/eleven-v3-conversational","voice":"george","input":"Hello from Hormouz.","response_format":"mp3"}' \
--output speech.mp3Specs
| Vendor | Elevenlabs |
|---|---|
| Type | Audio |
| Context window | — |
| Pricing | Previous price: $40/M charactersDiscounted price: $20/M characters−50% |
| API | speech |
Code example
curl https://api.hormouz.net/v1/audio/speech \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"elevenlabs/eleven-v3-conversational","voice":"george","input":"Hello from Hormouz.","response_format":"mp3"}' \
--output speech.mp3from 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="elevenlabs/eleven-v3-conversational",
voice="george",
input="Hello from Hormouz.",
response_format="mp3",
) as resp:
resp.stream_to_file("speech.mp3")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: "elevenlabs/eleven-v3-conversational",
voice: "george",
input: "Hello from Hormouz.",
response_format: "mp3",
});
await writeFile("speech.mp3", Buffer.from(await speech.arrayBuffer()));Buy the ElevenLabs: Eleven v3 Conversational API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches ElevenLabs: Eleven v3 Conversational 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.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Eleven v3 Conversational 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 Eleven v3 Conversational 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 Eleven v3 Conversational?
- Hormouz serves Eleven v3 Conversational 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 "george", and response_format to mp3 or pcm.
- Is Eleven v3 Conversational different from Eleven v3?
- It shares Eleven v3's languages and 5,000-character limit, but is tuned for dialogue in conversational agents, at a lower price per character.
Updated 2026-10-13