Cross-platform audio capture, playback, and processing for Node.js and browsers
decibri native binary for Linux x64
decibri native binary for Windows x64
decibri native binary for macOS arm64
decibri native binary for Linux arm64
Pi extension. Voice dictation via /voice — local on-device STT with sherpa-onnx Whisper (base multilingual int8), microphone capture via decibri.
Cross-browser microphone capture for the web. Same API as decibri for Node.js.
MCP server for voice I/O in AI agents. Part of the Decibri ecosystem.
Terminal chromatic instrument tuner (Node.js CLI) using tuner-core and decibri / PortAudio for microphone capture.
Cross-platform CLI for audio capture, playback, and device management. Zero runtime dependencies.
Give your AI agents the ability to listen. Microphone capture and speech-to-text tools for MCP-compatible agents.
Voice-powered terminal agent. Fully offline. Speak commands, get answers.
Neura — CLI for installing and managing the Neura AI assistant core service. Includes text chat and voice listen clients.
Cross-platform audio capture, playback, and voice activity detection for Rust
Cross-platform CLI for audio capture, playback, and device management
Safe Rust wrapper for sherpa-onnx speech recognition toolkit
Raw FFI bindings to the sherpa-onnx C API