Voice-powered terminal agent. Speak commands, get answers. Nothing leaves your machine.
Three steps, all on your machine. No cloud, no API keys, no network calls.
decibri captures microphone audio as raw PCM. Cross-platform, prebuilt binaries.
whisper.cpp converts speech to text locally. GPU-accelerated when available.
Your local LLM generates the answer. Any Ollama model. Default: llama3.2.
A voice interface that respects your machine, your data, and your workflow.
No cloud services. No API keys. No accounts. No recurring cost. Everything runs on your hardware.
Windows, macOS, and Linux. Prebuilt native binaries via decibri handle platform differences.
Works with any Ollama model. Swap models with --model mistral or use the default llama3.2.
No audio is recorded, stored, or transmitted. Ever. Your voice stays on your machine.
Apache 2.0 licensed. Inspect the code, contribute, or fork it. Built in the open on GitHub.
Run with --debug to see audio levels, capture duration, and raw whisper output.
Three commands. No configuration needed.
Minimal setup. No cloud accounts.
Built on proven open-source foundations.