The unified infrastructure layer for AI Agents and Voice AI.
Build real-time voice applications through a unified API for audio, speech, and AI integration across Python, Node.js, Rust, browsers, and the command line. From microphone to model to speaker, Decibri provides the infrastructure powering modern Voice AI.
The core audio library for AI Agents and Voice AI. Native bindings for Python, Node.js, Rust and browsers, with Silero VAD, sub-millisecond frame capture, and zero system dependencies.
Cross-platform audio CLI built on decibri. Capture, play, and list devices from any shell. One statically-linked binary, zero runtime dependencies.
Give your AI agents the ability to listen. Microphone capture and speech-to-text tools for MCP-compatible agents.
- ACE Process Buffer
- Acoustic Echo Cancellation (AEC)
See our website for the latest.
