Discover and explore top open-source AI tools and projects—updated daily.
Kokoro TTS is a command-line interface (CLI) tool that provides text-to-speech (TTS) capabilities using the Kokoro model. It is designed for users who need to convert text from various formats into natural-sounding speech directly from their terminal, offering features like multi-language support, voice blending, and processing of EPUB and PDF documents.
How It Works
Kokoro TTS leverages the Kokoro-ONNX model for speech synthesis. It processes input text from files (TXT, EPUB, PDF) or standard input, allowing for flexible integration into existing workflows. Key features include voice blending with customizable weights, enabling users to create unique vocal characteristics by mixing different voices. The tool also supports splitting output into chapters for organized audio files and offers streaming playback for immediate audio feedback.
Quick Start & Requirements
uv tool install kokoro-tts
or pip install kokoro-tts
. Alternatively, install from Git or clone and install locally.voices-v1.0.bin
and kokoro-v1.0.onnx
to the working directory.Highlighted Details
"voice1:60,voice2:40"
).Maintenance & Community
This is a personal project, and contributions via Pull Requests are welcome.
Licensing & Compatibility
Limitations & Caveats
Python 3.13+ is not currently supported. The project is described as a personal project, which may imply a smaller support or development community compared to larger, institutionally backed projects.
6 days ago
Inactive