---
title: "Kokoro-82M Clones Any Voice From a 3-Second Clip for Under $20"
subtitle: "A tiny 24MB adapter turns Kokoro-82M into a zero-shot voice cloner that enrolls a reference clip in under two seconds on CPU."
url: "https://alphasignal.ai/news/kokoro-82m-clones-any-voice-from-a-3-second-clip-for-under-20"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-10-07T16:00:10.786Z"
updated: "2026-10-07T16:03:31.727Z"
type: "Model"
topics:
  - "Audio"
  - "Post Training"
subtopics:
  - "Voice Cloning"
  - "Fine Tuning"
upvotes: 3646
source_url: "https://huggingface.co/remsky/kokoro-inno-clone-tuner"
comments: 0
truncated: true
---

# Kokoro-82M Clones Any Voice From a 3-Second Clip for Under $20

> A tiny 24MB adapter turns Kokoro-82M into a zero-shot voice cloner that enrolls a reference clip in under two seconds on CPU.

Kokoro-82M combines fast synthesis, stable output, and a library of fixed voice packs. The new [kokoro-inno-clone-tuner](https://huggingface.co/remsky/kokoro-inno-clone-tuner) adapter adds zero-shot voice matching, which creates a voice from an unseen reference clip without per-speaker training. It keeps the base model frozen and produces native Kokoro voice packs, so existing pipelines can use the result without changing synthesis models.

## A native voice pack from one clip

The adapter wraps [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) and converts reference audio into a tensor with Kokoro’s standard `[510, 1, 256]` shape. Applications can pass that tensor directly to `KPipeline` or save it as a reusable voice file with `torch.save`.

### Enroll and synthesize

```
# Shell
pip install inno-kokoro
```

```
import torch

from inno_kokoro.enroll import Tuner, enroll, read
from kokoro import KPipeline

tuner = Tuner()
pack, _ = enroll(*read("my_ref.wav"), tuner)

torch.save(pack, "my_voice.pt")

pipeline = KPipeline(lang_code="a")
result = next(
    pipeline("Hello from a tuned voice.", voice=pack)
)
audio = result.audio
```

Reference clips must be between 3 and 30 seconds, contain one speaker, and have reasonably clean audio. The current release supports English.

## Drop-in deployment, split licenses

[Kokoro-FastAPI](https://github.com/remsky/Kokoro-FastAPI) includes the tuner from version 0.9.0 onward, allowing self-hosted installations to add enrollment without rebuilding their serving layer. The bundled speaker encoder also avoids a separate model download.

* **Adapter code and weights:** Apache-2.0
* **Bundled speaker encoder:** CC BY-SA 3.0

Deployments that redistribute the full package should review the obligations of both licenses, particularly the attribution and share-alike terms attached to the speaker encoder.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [remsky/kokoro-inno-clone-tuner](https://huggingface.co/remsky/kokoro-inno-clone-tuner)
- [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M)
- [inno-kokoro on GitHub](https://github.com/remsky/inno-kokoro)
- [Kokoro-FastAPI](https://github.com/remsky/Kokoro-FastAPI)
