Analyze audio recordings for echo, loudness, speech intelligibility, and SNR.
npx skills add https://github.com/tenequm/skills --skill audio-quality-check
Please help me install this Agent Skill. Skill: audio-quality-check Source: https://github.com/tenequm/skills/tree/main/skills/audio-quality-check Command: npx skills add https://github.com/tenequm/skills --skill audio-quality-check
This Skill helps diagnose and understand why audio recordings sound bad, identifying issues like echo, poor speech clarity, and excessive noise.
Run the bundled analysis script on a recording directory by typing: python <skill-path>/scripts/analyze_recording.py "/path/to/recording/directory".
High-intent search queries and answers about installing and using this skill.
To detect echo and measure speech intelligibility in call recordings, you analyze the audio to identify duplicated signals and quantify clarity using metrics like STOI. This process isolates acoustic feedback and assesses overall speech quality.
Diagnosing excessive noise and poor SNR in M4A files involves spectral analysis to assess signal-to-noise ratio characteristics. This identifies background interference and evaluates why the recording sounds bad by quantifying noise levels.
Measuring loudness in LUFS and speech quality using PESQ involves processing the recording to extract objective quality metrics. This quantifies the audio volume levels and evaluates the perceptual quality of the speech signal.
Yes, you can analyze dual-track M4A files and AEC-processed audio recordings. The diagnostic process handles both single-track and dual-track formats to identify issues like echo, poor clarity, and excessive noise across different recording setups.
Yes, you need Python and libraries like librosa, numpy, scipy, and pyloudnorm to run audio recording diagnostics. These dependencies are required to execute the analysis scripts for measuring loudness, SNR, and detecting echo.
susamnBatch update metadata tags for audio and video files using ffmpeg.
bitwize-music-studioAnalyze WAV tracks for loudness, true peak, and tonal balance to master audio.
skinred78Automate video and audio processing with FFmpeg command-line guidance.
HelloEverybobyCapture real-time system audio and apply FFT for spectrum analysis.
