Added on Nov 18,2026

Decibri is an open-source audio layer for developers building AI agents and voice AI applications. It brings real-time microphone capture, speaker playback, echo cancellation and speech detection into one package for Python, Node.js and Rust.
It sits between an application and the operating system, capturing audio straight from the OS audio layer (WASAPI on Windows, CoreAudio on macOS and ALSA on Linux) with no subprocess, shell or intermediate encoding. Audio arrives in 100ms chunks by default and can be piped to files, WebSockets, speech-to-text services or voice agents.
Pre-built binaries ship for Windows, macOS and Linux on x64 and arm64, so Python and Node.js users install with a single pip or npm command and need no compilers or system audio libraries. The Rust crate is compiled from source by cargo.
Key features include a bundled Silero VAD model that runs locally through ONNX Runtime for machine learning voice activity detection, a Speaker API for full duplex audio, device selection by index or name, int16 or float32 output, asyncio support and bundled type definitions for each language.
The Node.js package also works in the browser, serving an AudioWorklet implementation when bundled with tools such as webpack or Vite. A one-line record_to_file helper covers simple recording jobs for ASR batch work or CI smoke tests.
Decibri outputs raw 16-bit PCM and has integration guides for AssemblyAI, AWS Transcribe, Azure, Deepgram, Google Cloud Speech-to-Text, Mistral Voxtral, OpenAI Realtime, Sherpa-ONNX and Whisper.cpp. Projects built on it include the voxagent terminal voice agent and the Wake Word extension for code editors.
Pricing: Decibri is free and released under the Apache-2.0 licence, with packages published on PyPI, npm and crates.io.
It is suited to developers building real-time transcription, wake word detection, voice assistants, streaming audio pipelines and server-side audio for voice agent backends, CLI tools and edge devices.
Popular alternatives to Decibri include Pollinations, NemoClaw and Agnes AI. Compare their pricing and what each is best for below.
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| OrcaRouter | Freemium | Developers and teams who want to balance AI quality and cost across many models. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
Leave a review for the community
No Review Found
Already a member? The same buttons sign you in.
We'll email you a 6-digit code. No password needed. By continuing you agree to our Privacy Policy.
We sent a 6-digit code to . It expires in 10 minutes.
No email? Check your spam folder, or ·