Decibri – unified audio layer for AI agents and Voice AI applications

Decibri launched a unified audio layer for AI agents and Voice AI applications, providing real-time microphone capture, speaker playback, and streaming to voice agents, WebSockets, or files via Python, Node.js, or Rust. The tool features built-in voice activity detection, zero system dependencies, and cross-platform support for macOS, Windows, and Linux, aiming to simplify real-time audio integration for developers.

The unified audio layer for AI agents and Voice AI applications Capture real-time microphone audio, play to speakers, or pipe anywhere voice agents, WebSockets, or files using Python, Node.js, or Rust. Built-in voice activity detection. Zero system dependencies. Zero setup. Install with one command: Then start streaming: python import decibri with decibri.Microphone sample rate=16000 as mic: for chunk in mic: print f"Got {len chunk } bytes" break js const { Microphone } = require 'decibri' ; const mic = new Microphone { sampleRate: 16000 } ; mic.on 'data', chunk = console.log Got ${chunk.length} bytes ; setTimeout = mic.stop , 5000 ; use std::time::Duration; use decibri::{DecibriError, Microphone, MicrophoneConfig}; fn main - Result< , Box<dyn std::error::Error { let capture = Microphone::new MicrophoneConfig::default ?; let stream = capture.start ?; loop { match stream.next chunk 1600, Some Duration::from millis 100 { Ok Some chunk = println "Got {} samples", chunk.data.len , Ok None = continue, Err DecibriError::MicrophoneStreamClosed = break, Err e = return Err e.into , } } Ok } Real-time audio capture and playback is harder than it should be Designed for real-time systems Built for real-time audio. Pre-built binaries for Python, Node.js, and Rust mean no compilers, no system audio libraries, and no setup. Cross-platform macOS, Windows, and Linux with pre-built binaries. No build tools required on any platform. Direct capture 100ms audio chunks by default 1600 frames at 16kHz . cpal captures directly from the OS audio layer with no subprocess, no shell, and no intermediate encoding. Stream-native Python iterators, Node.js Readable streams, and Rust channels. Pipe to files, WebSockets, or voice agents using each language's native idioms. Zero dependencies No system audio libraries, no build tools, no install scripts. Rust and cpal compiled into a single package per language. Type-safe Bundled type definitions for Python typing stubs , Node.js TypeScript .d.ts , and Rust native types . Full IDE autocomplete and inline documentation. Configurable Sample rate, channels, frames per buffer, device selection by index or name, int16 or float32 output, and optional voice activity detection with speech/silence events. Audio output Play audio through the system speaker. Decibri's Speaker API works as a standard write target you can pipe capture into for full duplex audio. ML voice detection Bundled Silero VAD v5 model for accurate speech detection in noisy environments. Runs locally in Rust via ONNX Runtime with no cloud API needed. Browser support The Node.js package ships with browser support out of the box. Conditional exports serve an AudioWorklet implementation when bundled for browsers. Pre-built binaries, zero setup Pre-compiled native binaries ship inside the package. No build tools, no compilation, no post-install downloads. Built for real-time voice applications Record audio to disk Decibri provides a one-line record to file helper for the simple case, and full streaming control when you need it. Set the sample rate to match your target format. No encoding step, no intermediate buffers. python import decibri decibri.record to file "capture.wav", duration seconds=10, sample rate=16000 js const { Microphone } = require 'decibri' ; const fs = require 'fs' ; const mic = new Microphone { sampleRate: 16000, channels: 1 } ; mic.pipe fs.createWriteStream 'capture.raw' ; use decibri::sample::f32 to i16 le bytes; use decibri::{Microphone, MicrophoneConfig}; use std::fs::File; use std::io::Write; fn main - Result< , Box<dyn std::error::Error { let mut file = File::create "capture.raw" ?; let capture = Microphone::new MicrophoneConfig::default ?; let stream = capture.start ?; while let Ok Some chunk = stream.next chunk 1600, None { file.write all &f32 to i16 le bytes &chunk.data ?; } Ok } Audio infrastructure for real-time applications Decibri sits between your application and the operating system. It captures from microphones, plays to speakers, and runs voice activity detection, all in real-time. Use it when you need predictable, low-latency audio I/O without managing system dependencies or platform differences. Decibri is built for: - ✓Real-time microphone capture in Python, Node.js, or Rust applications - ✓Streaming PCM audio to speech-to-text services, voice agents, or WebSocket pipelines - ✓Local wake word detection with bundled Silero VAD - ✓Recording audio to file for ASR batch jobs or CI smoke tests - ✓Cross-platform deployment Windows, macOS, Linux without system audio dependencies - ✓Server-side audio in voice agent backends, CLI tools, and edge devices Works with your existing stack Decibri outputs raw 16-bit PCM, the standard format expected by speech and audio processing engines. See the integration guides for working examples. Cloud /docs/integrations/stt/assemblyai AssemblyAI Real-time cloud speech-to-text with turn-based transcription Cloud /docs/integrations/stt/aws-transcribe AWS Transcribe Real-time cloud speech-to-text with Amazon Transcribe streaming Cloud /docs/integrations/stt/azure Azure Real-time cloud speech-to-text with Azure Speech-to-Text Cloud /docs/integrations/stt/deepgram Deepgram Real-time cloud speech-to-text with Deepgram's Nova-3 model Cloud /docs/integrations/stt/google Google Real-time cloud speech-to-text with Google Cloud Speech-to-Text Cloud /docs/integrations/stt/mistral-voxtral Mistral Real-time cloud speech-to-text with Voxtral open-weights model Cloud /docs/integrations/stt/openai OpenAI Real-time cloud speech-to-text with OpenAI's Realtime API Local /docs/integrations/stt/whisper-cpp Whisper.cpp Local speech-to-text transcription with OpenAI's Whisper model Decibri outputs raw PCM, the standard format used by Vosk, openWakeWord, and any audio processing engine. Products powered by Decibri Tools that use decibri as their audio capture layer. From voice agents to wake phrase detection. voxagent decibri + whisper.cpp + Ollama https://voxagent.run Voice-powered terminal agent. Speak commands, get answers. Fully offline using whisper.cpp for local transcription and Ollama for local LLM inference. No cloud, no API keys. Wake Word decibri + sherpa-onnx + VS Code API https://wakeword.io Voice activation for code editors. Say "Hey Claude" and Claude opens. Say "Hey Copilot" and Copilot opens. Fully local wake phrase detection using sherpa-onnx. Zero config. Common questions 16-bit signed integer PCM, little-endian by default. A 32-bit float format is also available. The default is the raw format expected by most speech and wake-word engines including Vosk, sherpa-onnx, and whisper.cpp. No. Decibri uses cpal for direct OS audio access. There are no system audio libraries to install. No. Pre-built binaries ship with the package on every supported platform: Python wheels , Node.js optional platform packages , and Rust compiled at install time via cargo . No compilers, no node-gyp, no Visual Studio Build Tools, no Xcode required. Yes. Decibri works in both Node.js and the browser from a single package. When bundled for the browser webpack, vite, etc. , conditional exports serve the browser implementation automatically. No separate package needed. See the browser documentation /docs/apis/browser . Yes. Use Microphone.devices to list available input devices, then pass the device index or a name substring to the constructor options. Node.js 18 and above. Apache-2.0. Decibri supports Python 3.10 and above on Windows, macOS, and Linux. Prebuilt wheels are published for Linux x64, Linux ARM64, macOS Apple Silicon, and Windows x64. Yes. Decibri ships AsyncMicrophone, AsyncSpeaker, and async record to file as proper async classes that work as async context managers with async for iteration. Audio capture runs on a separate thread, so the event loop isn't blocked. The recommended pattern is async with await decibri.AsyncMicrophone.open ... as mic: async for chunk in mic: ... The open factory dispatches the optional Silero VAD model load off the event loop. Rust gives decibri direct OS audio access via cpal, a cross-platform Rust audio library. The Rust core compiles to native code on every supported platform, so the same audio engine powers the Python, Node.js, and Rust packages. Memory safety enables real-time audio code without manual buffer management. The result: predictable low-latency audio with zero system dependencies. Start streaming audio in minutes One install. One import. Real-time microphone audio.