opendunes

Kokoro 82M

by HexgradReleased 23 April 2026

Kokoro 82M turns text into speech and gives you audio, with 54 ready-made voices sorted by language and gender. It speaks eight languages: Chinese, Spanish, Portuguese, Japanese, Italian, French, Hindi and English, the last in American and British accents. Use it for narration, read-aloud features and spoken replies in those languages.

TakesText
GivesAudio
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,80 DA per paragraph read aloud3 000 DA buys about 3 700 paragraphs read aloud

One paragraph read aloud, the ordinary use

600 characters sent× 1 331,34 DA per 1M0,80 DA
Total≈ 0,80 DA

Every rate

Meter↑ you send↓ comes back
Characters1 331,34 DA

per 1M characters

Read a short notification≈ 0,13 DA
Record a phone menu greeting≈ 0,27 DA
Voice a 30-second product ad≈ 0,60 DA
Read a 600-character paragraph aloud≈ 0,80 DA
Read a one-page article aloud≈ 3,99 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

Two companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M characters: ↑ what you send.

DeepInfraUnited States…
↑
206,36
Latency
…
Together…
↑
1 331,34
Latency
…
Provider↑ SentLatencyUptime
DeepInfraUnited States206,36……
Together1 331,34……

You pay the price of the provider that served your request. Prices read 15:48 · speed over the last 30 minutes · uptime over 3 days.

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/audio/speech
Base URL
https://opendunes.com/v1
Model ID
hexgrad/kokoro-82m
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

with client.audio.speech.with_streaming_response.create(
    model="hexgrad/kokoro-82m",
    input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
    voice="af_alloy",
) as resp:
    resp.stream_to_file("speech.mp3")
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Questions about Kokoro 82M

  • How much does Kokoro 82M cost in dinars?

    About 0,80 DA per paragraph read aloud. ↑ 1 331,34 DA per 1M characters.

  • Is Kokoro 82M free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Kokoro 82M best for?

    Kokoro 82M turns text into speech and gives you audio, with 54 ready-made voices sorted by language and gender. It speaks eight languages: Chinese, Spanish, Portuguese, Japanese, Italian, French, Hindi and English, the last in American and British accents. Use it for narration, read-aloud features and spoken replies in those languages.

  • How do I pay for Kokoro 82M without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Kokoro 82M included, is paid from that balance. No foreign card, no conversion.

  • Does Kokoro 82M work in Arabic, French or Darja?

    hexgrad lists American and British English, Japanese, Mandarin Chinese, Spanish, French, Hindi, Italian and Brazilian Portuguese. Arabic and Darja are not named.

  • How many voices, and can it clone mine?

    54 voices. Cloning from a sample: not stated.

  • Who makes Kokoro 82M, and when was it released?

    Hexgrad. Released 23 April 2026.