KokoClone extends Kokoro TTS with zero-shot voice cloning. Type text, upload a short voice sample, and generate multilingual speech in that voice instantly. Built for speed with real-time friendly inference, CPU support, and a clean API for developers building voice assistants, agents, and speech applications.
Hey everyone! I’m Ashish, the creator of KokoClone.
I’ve been experimenting a lot with Kokoro TTS recently and loved how fast and expressive it is. But I kept wondering what it would be like if Kokoro could also do voice cloning without losing that speed.
So I built KokoClone — a lightweight pipeline that adds zero-shot voice cloning on top of Kokoro while keeping it fast and real-time friendly.
You can type text, upload a short voice sample, and generate multilingual speech in that voice.
I’d really love to hear your feedback — especially on the voice quality, speed, and possible use cases.
Thanks for checking it out! 🙌
HanaVerse