Generated by Code IQ · v1.0

moonshine
Knowledge Tutorial

A chapter-by-chapter walkthrough of moonshine, generated from its source code and tutorial markdown.

7
Chapters
-
Subsystems
∞
Rabbit Holes
▶ Start Reading ⎇ View on GitHub
System Architecture

How the pieces fit

moonshine is organized as connected concepts and components. Start broad, then drill down chapter by chapter.

⚙️
Transcriber (The Orchestrator)
Transcriber (The Orchestrator)
⚙️
MicTranscriber (Live Input Handler)
MicTranscriber (Live Input Handler)
⚙️
Event Listener System
Event Listener System
⚙️
Intent Recognizer (Action Dispatcher)
Intent Recognizer (Action Dispatcher)
⚙️
Voice Activity Detection (VAD)
Voice Activity Detection (VAD)
⚙️
Streaming Inference Engine
Streaming Inference Engine
⚙️
Cross-Platform Bindings (C API Bridge)
Cross-Platform Bindings (C API Bridge)
moonshine — bash
➜open tutorial
◆ Scanning numbered chapters
◆ Building navigation and Mermaid diagrams
◆ Generating chapter and subsystem pages
✓ 7 chapter pages built
✓ Theme toggle enabled
➜
Repository Overview

Intro and Architecture Diagram

Moonshine is a lightweight, fast speech-to-text library designed for real-time applications on edge devices and the cloud. At its core, a Transcriber orchestrates the flow of audio through Voice Activity Detection and a Streaming Inference Engine to produce low-latency text. Developers can build interactive voice experiences by using Intent Recognizers and subscribing to transcription updates via a flexible Event Listener System.

Source Repository: https://github.com/moonshine-ai/moonshine

flowchart TD A0["Transcriber (The Orchestrator)"] A1["MicTranscriber (Live Input Handler)"] A2["Intent Recognizer (Action Dispatcher)"] A3["Streaming Inference Engine"] A4["Event Listener System"] A5["Cross-Platform Bindings (C API Bridge)"] A6["Voice Activity Detection (VAD)"] A0 -->|"Uses for inference"| A3 A0 -->|"Segments audio with"| A6 A0 -->|"Notifies"| A4 A1 -->|"Wraps and feeds"| A0 A5 -->|"Exposes core of"| A0 A2 -->|"Implements"| A4
Tutorial Chapters

All 7 chapters

Follow sequentially or jump to any topic. Start with Transcriber (The Orchestrator).

Ch.01 CORE
Transcriber (The Orchestrator)
Welcome to the Moonshine library! If you are looking to turn speech into text, you have come to the right place.
↗
Ch.02 CORE
MicTranscriber (Live Input Handler)
Welcome back! In the previous chapter, Transcriber (The Orchestrator), we learned about the "Project Manager" that coordinates the AI model…
↗
Ch.03 CORE
Event Listener System
Welcome to Chapter 3! In the previous chapter, MicTranscriber (Live Input Handler), we learned how to capture audio from the microphone aut…
↗
Ch.04 CORE
Intent Recognizer (Action Dispatcher)
Welcome to Chapter 4! In the previous chapter, Event Listener System, we built a news feed that notifies us when a user finishes a sentence.
↗
Ch.05 CORE
Voice Activity Detection (VAD)
Welcome to Chapter 5! In the previous chapter, Intent Recognizer (Action Dispatcher), we learned how to turn text into actions.
↗
Ch.06 CORE
Streaming Inference Engine
Welcome to Chapter 6! In the previous chapter, Voice Activity Detection (VAD), we learned how to detect when a user is speaking to chop aud…
↗
Ch.07 CORE
Cross-Platform Bindings (C API Bridge)
Welcome to the final chapter of the Moonshine tutorial!
↗
About This Project

Generated by Code IQ

This tutorial was automatically generated by Code IQ and rendered with the shared tutorial site builder. It can be produced for any repository tutorial folder that follows the numbered markdown chapter layout.

View Code IQ ↗
python build_site.py '/home/runner/work/Code-IQ/Code-IQ/output/moonshine'

// → 7 chapters
// → source: moonshine-ai/moonshine