Marketplace · Text-to-speech
speaches-ai/Kokoro-82M-v1.0-ONNX
Call speaches-ai/Kokoro-82M-v1.0-ONNX through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.
At a glance.
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
audio = client.audio.speech.create(
model="speaches-ai/Kokoro-82M-v1.0-ONNX",
input="Hello from the grid.",
)speaches-ai/Kokoro-82M-v1.0-ONNX in detail.
Run this model using [speaches](https://github.com/speaches-ai/speaches)
- Published by
- speaches-ai
- Parameters
- 82M
- Download size
- 354 MB (weights on Hugging Face)
- Format
- onnx
- Licence
- Apache 2.0
- Based on
- hexgrad/Kokoro-82M
- Task
- text to speech
- Library
- onnx
- Languages
- multilingual
- First published
- 20 Mar 2025
- Last updated
- 21 Mar 2025
- Likes
- 2
onnx speaches kokoro text-to-speech multilingual
The model card
Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.
Run this model using speaches
WARN: the structure of this model repository is experimental and will change in the near future.
Sources: speaches-ai/Kokoro-82M-v1.0-ONNX on Hugging Face. Collected from public sources on 15 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Who's serving it.
Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| GTX 1080 Ti (11G) | L1 | £0.026 /h audio | 60 chars/s | 78 | loads on request | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
Right now one machine serves speaches-ai/Kokoro-82M-v1.0-ONNX. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.
Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load speaches-ai/Kokoro-82M-v1.0-ONNX, and the platform benchmarks it on your hardware before your first request.