← Discover
GitHub · moonshine-ai/moonshine↑ +282 today

Real-time AI voice tools

Moonshine offers low-latency speech to text, intent recognition and text to speech capabilities for voice interfaces and artificial intelligence agents. This library, developed in C++ language, aims to optimize real-time audio processing processes.

Updates

  • November 6, 2026: Stars 10,945 → 11,422, latest release v0.1.6 (November 6, 2026).
  • August 27, 2026: Stars 10,886 → 10,945, latest release v0.1.5 (August 24, 2026).
  • August 18, 2026: Stars 10,853 → 10,886, latest release v0.1.3 (August 18, 2026).
  • August 15, 2026: Stars 10,671 → 10,853, latest release v0.1.2 (August 13, 2026).

What you get

  • Fast and discreet audio processing running on-device
  • Low latency optimized for live broadcasts
  • Ability to convert speech to text and text to audio

Installation

Installation with Python
pip install moonshine-voice
moonshine-voice mic --language en
Raspberry Pi installation
sudo pip install --break-system-packages moonshine-voice
 moonshine-voice mic --language en

Running it

Live transcription via microphone
moonshine-voice mic --language en

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to develop a voice interface using the Moonshine library. Help me create the basic Python code structure needed to convert the sound coming from my microphone into text in real time and perform intent recognition operations on this text. Also, explain the configuration settings I should pay attention to for the system to run with low latency.

Repository: https://github.com/moonshine-ai/moonshine. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Artificial Intelligence
Who it is forIt is for developers who want to develop low-latency and privacy-oriented voice artificial intelligence applications that run on the device.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-21: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.