Bark Voice Cloning is a Hugging Face Space that uses the Bark text-to-speech model to clone a speaker's voice. Users upload an audio file; the last 20 seconds are analyzed to create a voice embedding. The resulting cloned voice can then be used to generate new speech from text. It is aimed at rapid voice personalization for audio projects.
In the Voice, TTS & speech space, Bark Voice Cloning takes a focused approach. It focuses on replicating a specific voice from a short recording for use in speech synthesis. It is built as a consumer product for content creators and developers. Bark Voice Cloning is free to use. Bark Voice Cloning is available on the web, and it can be self-hosted.
GitMylo builds and maintains Bark Voice Cloning, and it first shipped in 2023. Among its 3 catalogued features are Voice Cloning, Audio Upload, and TTS Generation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do