onnxruntime-node: MIT Licenseespeak: GNU GPL v3flite: BSD Licensepico: Apache License 2.0sam: Abandonware / fair-use / unknownvoskApache License 2.0tinyldMIT Licensefasttext: MIT LicensefvadBSD-3-Clausekissfft: BSD-3-Clausepffft: BSD-3-Clausernnoise: BSD-3-Clausesonic: Apache License 2.0speex-resampler: BSD-3-Clauserubberband: GNU GPL v2compromise: MIT Licensecldr-segmentation: MIT Licensejieba-wasm: MIT Licensekuromoji: Apache License 2.0tiktoken: MIT License
A large variety of voices, models and binaries are served from the repository.
All are freely distributable, with varying licenses:
- Flite voices (
flite-): BSD License - SVOX Pico resources (
pico-): Apache License 2.0 - Silero VAD (
silero-vad) and Silero language classifier (silero-lang-classifier-95): MIT License - Silero speech recognition models (
silero-en-,silero-de-,silero-es-,silero-ua-): BY-NC-SA - VITS pre-trained models (
vits-): licensed under various creative commons licenses: CC0, CC-BY and BY-NC-SA, and few are public domain. You can view the individual license for each model in the model cards on the Piper samples page - Whisper pre-trained models (
whisper-): MIT License - MDX-NET source separation models (
mdxnet-): MIT License nsnet2: Attribution 4.0 International
Tool binary distributions
- FFmpeg: LGPL, GPL v2 and GPL v3 Licenses
- SoX: GPL v2 License
- whisper.cpp: MIT License