Libraries & frameworks
ten-vad
TEN-framework/ten-vad
TEN VAD is a lightweight, low-latency voice activity detector distributed as cross-platform libraries with Python, Java, Go and JS bindings plus an ONNX model.
Topics
Related projects
roc-toolkit1.3kRoc Toolkit is a C library and command-line toolset for real-time audio streaming over networks, featuring guaranteed latency, packet-loss recovery, clock conversion and CD-quality sound.
ffsubsync7.9kFFsubsync is a command-line tool that automatically synchronizes subtitles with video using voice activity detection and FFT-based alignment, correcting offsets and framerate drift.
FFmpeg66.6kA complete multimedia toolkit with libraries and command-line tools for encoding, decoding, and streaming audio and video.
pathway62kA Python ETL framework for batch and streaming analytics with a Rust engine, connectors and LLM/RAG helpers.
howler.js25.4kA JavaScript audio library for the modern web that unifies Web Audio and HTML5 Audio, with sound sprites, spatial audio and broad codec support.
FunASR21kAn industrial speech recognition toolkit covering training, inference, streaming ASR, VAD, punctuation, speaker diarization and OpenAI-compatible serving.