audio-injection-testing

Community

Automate audio-based testing for wake word & STT.

Authorwant2bet
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables testing Bob The Skull using virtual audio devices, removing the need to repeatedly speak wake words. It helps validate wake word detection, STT accuracy, and the end-to-end conversation pipeline with automated audio injection and troubleshooting steps.

Core Features & Use Cases

  • Automated Wake Word Testing: Run hundreds of audio injections to verify wake word detection.
  • STT Accuracy Evaluation: Inject pre-recorded phrases and compare transcripts.
  • Full Pipeline Testing: Validate the entire pipeline from wake word to LLM response and TTS.
  • Troubleshooting Guidance: Provides setup, configuration, and debugging tips for common issues.

Quick Start

  • Run the virtual audio setup: python3 setup_combined_audio.py
  • Execute a test sequence: python3 test_wake_word_inject.py test --files audio/static/testing/wake_up_bob.mp3 audio/static/testing/hey_bob.mp3 --delay 2.0
  • Monitor logs for results: tail -f logs/bob.log

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: audio-injection-testing
Download link: https://github.com/want2bet/BobTheSkull5/archive/main.zip#audio-injection-testing

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.