Kokoro-82M-Swift
Built by mweinbach, Kokoro-82M-Swift is an speech-and-audio model. Kokoro-82M-Swift is an open-weights audio model.
by mweinbach
Best for
Ways to use Kokoro-82M-Swift in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your mweinbach API key. osFoundry discovers Kokoro-82M-Swift automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
Kokoro-82M-Swift is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Kokoro-82M-Swift vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Kokoro-82M-Swift | mweinbach | — | — | Free (local) | Yes |
| Codec | ktvoice | — | — | Free (local) | Yes |
| hviske-v5.2 | syvai | — | — | Free (local) | Yes |
| distil-large-v3.5-ONNX | distil-whisper | — | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about Kokoro-82M-Swift
Is Kokoro-82M-Swift free to use?
Kokoro-82M-Swift is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use Kokoro-82M-Swift commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run Kokoro-82M-Swift locally?
Yes. Kokoro-82M-Swift is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is Kokoro-82M-Swift best at?
Kokoro-82M-Swift is well-suited to text to speech.
How do I use Kokoro-82M-Swift in osFoundry?
Paste your mweinbach API key in the key dialog (or deploy the open weights for self-hostable models), assign Kokoro-82M-Swift to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by mweinbach on April 6, 2026. Source: https://huggingface.co/mweinbach/Kokoro-82M-Swift