Kokoro 82M API.
Let your product speak.

Kokoro 82M is a text-to-speech model for turning written content into audio. Evaluate spoken responses, short narration and read-aloud features through Blade’s catalogue.

€5 in free credits for every new customer.

Try Kokoro 82M

From €0.00399 per audio minute. View the pricing details.

Text to speech
with Kokoro 82M.

Practical starting points for Kokoro 82M. Choose one task, define the expected output and measure the result on your own examples.

Read product content aloud

Turn approved text into an audio alternative. Check pronunciation, pace and the controls your interface gives the listener.

Add spoken replies

Generate audio from a reviewed assistant response. Keep the text response available so users can read or replay it.

Draft short narration

Try voice output for onboarding or short explainers. Listen to names, numbers and abbreviations before publishing.

Explore the text to speech workflow ↗

Kokoro 82M pricing

Kokoro 82M
API pricing.

These are catalogue “From” rates in EUR. Dynamic pricing can change the applicable price. Confirm your model, request route and active billing unit before estimating a workload.

See Kokoro 82M on the rate card ↗

Per audio minute: From€0.00399

A concrete example
60 audio minutes = €0.239400 at the displayed starting rates.

Illustration only; excludes retries, other models and paid tools. Confirm whether the billed duration is generated audio for your route. Catalogue updated 2026-10-22.

Check current rates ↗

API integration

How to use
the Kokoro 82M API.

Use the Blade model ID kokoro-82m and keep your API key in your backend environment. Verify account access and supported parameters before connecting production traffic.

Create a Blade API key in the console.
Run pip install openai and set BLADE_API_KEY.
Check the model list below, then use the console’s confirmed inference example for this model.

Read the API reference ↗

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.models.blade.sh/v1",
    api_key=os.environ["BLADE_API_KEY"],
    timeout=120.0,
)

model_id = "kokoro-82m"
models = client.models.list()
match = next(
    (item for item in models.data
     if item.id == model_id),
    None,
)
if match is None:
    raise RuntimeError("Model not listed for this account")
print(match.model_dump_json(indent=2))

Install openai and set BLADE_API_KEY. This checks the account’s model list; it does not run inference. Copy the confirmed model-specific inference request from the console before integrating.

Kokoro 82M API FAQ.

What can I use Kokoro 82M for?

Kokoro 82M is a text-to-speech model for turning written content into audio. Evaluate spoken responses, short narration and read-aloud features through Blade’s catalogue. Its Blade model ID is kokoro-82m.

How much does Kokoro 82M cost on Blade?

Per audio minute: from €0.00399. These are dynamic catalogue starting rates as of 2026-10-22, not fixed prices for every request. Check the console for current rates.

What should I confirm before integrating?

The current speech API documentation describes an Orpheus wrapper, not a verified Kokoro configuration. Confirm the Kokoro route, voices, output formats and language support in the console before integrating.

Model reference: Publisher model reference ↗. Hosted configuration and pricing: Blade catalogue, 2026-10-22.

Choose by task, input type and billing unit. Browse all models ↗

Kokoro 82M API.Let your product speak.

Text to speechwith Kokoro 82M.