Batch Audio Diagnostic (Up to 50 Files)

Runs full diagnostic analysis on multiple files in parallel. Processes up to 50 files at once and returns per-file results plus a summary comparison. Sample rate mismatches between files are flagged as dealbreaker severity.

Parameters

Parameter Type Default Description
file_paths list[string] required List of paths to audio files (max 50)

Example Output

$ batch_diagnostic [vocals.wav, drums.wav, bass.wav, keys.wav]

Batch Diagnostic: 4 files

vocals.wav Loudness: -18.4 LUFS | Peak: -3.2 dB | Centroid: 2,847 Hz Problems: SIG sibilance at 6.8 kHz

drums.wav Loudness: -12.1 LUFS | Peak: -0.4 dB | Centroid: 1,423 Hz Problems: None

bass.wav Loudness: -16.7 LUFS | Peak: -2.8 dB | Centroid: 185 Hz Problems: MOD mud 200-350 Hz

keys.wav Loudness: -20.3 LUFS | Peak: -6.1 dB | Centroid: 3,102 Hz Problems: None

Summary: Loudest: drums.wav (-12.1 LUFS) Quietest: keys.wav (-20.3 LUFS) Range: 8.2 LUFS between stems Issues: 2 files have detected problems

What the Numbers Mean

Batch diagnostic returns a condensed version of each file’s full diagnostic (key metrics only), plus a cross-file summary:

  • Range between stems — The LUFS difference between loudest and quietest. A large range (>10 LU) might mean some stems need gain staging before mixing.
  • Per-file problems — Quick identification of which stems need treatment before mixing begins.
  • Sample rate mismatch — If stems don’t share a sample rate, batch_diagnostic flags this as a dealbreaker. Mismatched rates will cause timing issues in your DAW.

See full_diagnostic for complete metric descriptions.

Example Prompts

Session overview

Analyze all the stems in my session: vocals.wav, drums.wav, bass.wav, guitar.wav, keys.wav, strings.wav

Quick scan

Run a batch diagnostic on everything in my recordings folder

  • full_diagnostic — Deep analysis on a single file (more detail per file)
  • multi_stem_masking — After batch diagnostic, check for frequency conflicts between stems

Pro tip

Run batch diagnostic before starting a mix session. It gives you a bird’s-eye view of all your material: relative loudness, which tracks have issues, and where the potential trouble spots are. Your AI assistant can then prioritize what to fix first.