awesome-repositories.com
Blog
awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektÜber unsRanking-MethodikPresseMCP-Server
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
ricky0123 avatar

ricky0123/vad

0
View on GitHub↗
2,000 Stars·266 Forks·TypeScript·3 Aufrufewww.vad.ricky0123.com↗

Vad

This library is a browser-based utility for real-time voice activity detection. It monitors live microphone input to distinguish between background noise and human vocalizations, enabling applications to identify when a person begins or stops speaking.

The project utilizes WebAssembly to execute signal processing logic within the browser sandbox, ensuring high-performance analysis of audio buffers. It integrates directly with the native audio graph to capture raw pulse-code modulation data, employing an energy-threshold approach to identify speech boundaries.

The library provides an event-driven architecture that triggers asynchronous notifications for speech start and end events. It also supports the automated extraction of audio samples into data arrays once a speech segment concludes, facilitating further processing or storage.

Features

  • Voice Activity Detection - Provides real-time voice activity detection to identify when a user is speaking.
  • Speech Boundary Detection - Identifies the start and end of human speech segments within live audio streams.
  • Real-Time Speech Processing - Processes live audio in real-time to isolate speech for downstream analysis or transcription.
  • Speech Activity Detection - Uses energy-based amplitude thresholds to classify audio frames as speech or background noise.
  • Speech Segment Extraction - Extracts and isolates audio samples into data arrays once a speech segment is identified.
  • Audio Digital Signal Processing - Performs high-performance signal processing on audio buffers using compiled code in the browser sandbox.
  • Raw Audio Captures - Captures raw PCM audio data directly from hardware microphones via the browser audio graph.
  • Real-Time Microphone Captures - Monitors live microphone input to distinguish between background noise and human vocalizations.
  • Voice Interaction Interfaces - Enables the development of responsive voice-controlled interfaces that react to user speech.

Star-Verlauf

Star-Verlauf für ricky0123/vadStar-Verlauf für ricky0123/vad

KI-Suche

Entdecke weitere awesome Repositories

Beschreibe in einfachen Worten, was du brauchst — die KI bewertet tausende kuratierte Open-Source-Projekte nach Relevanz.

Start searching with AI

Kuratierte Suchen mit Vad

Handverlesene Sammlungen, in denen Vad vorkommt.
  • Voice activity detection

Häufig gestellte Fragen

Was macht ricky0123/vad?

This library is a browser-based utility for real-time voice activity detection. It monitors live microphone input to distinguish between background noise and human vocalizations, enabling applications to identify when a person begins or stops speaking.

Was sind die Hauptfunktionen von ricky0123/vad?

Die Hauptfunktionen von ricky0123/vad sind: Voice Activity Detection, Speech Boundary Detection, Real-Time Speech Processing, Speech Activity Detection, Speech Segment Extraction, Audio Digital Signal Processing, Raw Audio Captures, Real-Time Microphone Captures.

Welche Open-Source-Alternativen gibt es zu ricky0123/vad?

Open-Source-Alternativen zu ricky0123/vad sind unter anderem: snakers4/silero-vad — Silero VAD is a voice activity detection model and deep learning speech classifier designed to distinguish human… k2-fsa/sherpa-ncnn — Sherpa-ncnn is an edge-based speech recognition and synthesis engine designed to run neural network models locally on… huggingface/speech-to-speech — This project is a framework for building local voice assistants and a real-time audio streaming server. It functions… koljab/realtimestt — RealtimeSTT is a local speech-to-text engine and real-time automatic speech recognition server. It utilizes… ggerganov/kbd-audio — This project is an acoustic keystroke recognition system and audio side-channel analysis tool. It identifies typed… julius-speech/julius — Julius is a high-performance, open-source speech recognition engine designed for large vocabulary continuous speech…

Open-Source-Alternativen zu Vad

Ähnliche Open-Source-Projekte, sortiert nach der Anzahl der gemeinsamen Funktionen mit Vad.
  • snakers4/silero-vadAvatar von snakers4

    snakers4/silero-vad

    8,209Auf GitHub ansehen↗

    Silero VAD is a voice activity detection model and deep learning speech classifier designed to distinguish human speech from silence across diverse languages and noisy environments. It functions as a pre-trained neural network capable of identifying speech segments within both static audio recordings and real-time data streams. The project includes a language identification tool for classifying spoken languages and a framework for fine-tuning audio models. It provides utilities for optimizing detection thresholds using validation datasets and retraining the model with custom labeled audio to

    Pythononnxonnx-runtimeonnxruntime
    Auf GitHub ansehen↗8,209
  • k2-fsa/sherpa-ncnnAvatar von k2-fsa

    k2-fsa/sherpa-ncnn

    1,743Auf GitHub ansehen↗

    Sherpa-ncnn is an edge-based speech recognition and synthesis engine designed to run neural network models locally on mobile, embedded, and desktop hardware. It provides a cross-platform framework for offline speech-to-text transcription and text-to-speech synthesis, ensuring that all audio processing occurs on-device without requiring an internet connection or external cloud services. The project distinguishes itself through its use of the ncnn inference engine, which is optimized for low-latency execution on resource-constrained devices. It incorporates on-device model quantization to reduc

    C++asrccpp
    Auf GitHub ansehen↗1,743
  • huggingface/speech-to-speechAvatar von huggingface

    huggingface/speech-to-speech

    4,895Auf GitHub ansehen↗

    This project is a framework for building local voice assistants and a real-time audio streaming server. It functions as a containerized inference engine and a multilingual speech pipeline that orchestrates speech-to-text, language models, and text-to-speech components to convert spoken input into spoken output. The system is distinguished by its use of WebSocket-based bidirectional streaming for low-latency interactions. It features a voice activity detection system that manages speech boundaries and handles user barge-in interruptions during assistant playback. It also supports custom voice

    Pythonaiassistantlanguage-model
    Auf GitHub ansehen↗4,895
  • koljab/realtimesttAvatar von KoljaB

    KoljaB/RealtimeSTT

    9,477Auf GitHub ansehen↗

    RealtimeSTT is a local speech-to-text engine and real-time automatic speech recognition server. It utilizes transformer-based recognition and omnilingual pipelines to convert live audio streams into text, providing a WebSocket-based streaming API for raw PCM audio transmission. The project is distinguished by a dual-backend transcription pipeline that uses a lightweight engine for immediate partial suggestions and a heavier model for final high-accuracy results. It includes a wake word detection system to trigger recording and employs a shared-resource inference model to distribute heavy spee

    Pythonpythonrealtimespeech-to-text
    Auf GitHub ansehen↗9,477
    • Alle 30 Alternativen zu Vad anzeigen→