ricky0123/vad
A TypeScript library that runs the Silero VAD neural network model in the browser using ONNX Runtime Web for real-time voice activity detection.
Not currently ranked — collecting fresh signals.
star history
This package provides a voice activity detector that runs entirely in the browser. It uses the Silero VAD deep learning model converted to ONNX format and executed via ONNX Runtime Web, enabling accurate speech detection from microphone input without server-side processing. Developers can integrate it to trigger callbacks when speech is detected, making it useful for speech-to-text applications, voice-controlled interfaces, or UI feedback during user speech.
Frequently asked
- What is ricky0123/vad?
- A TypeScript library that runs the Silero VAD neural network model in the browser using ONNX Runtime Web for real-time voice activity detection.
- Is vad open source?
- Yes — ricky0123/vad is an open-source project tracked on heatdrop.
- What language is vad written in?
- ricky0123/vad is primarily written in TypeScript.
- How popular is vad?
- ricky0123/vad has 2k stars on GitHub.
- Where can I find vad?
- ricky0123/vad is on GitHub at https://github.com/ricky0123/vad.