Describe Rename Sound Files

SoundTag AI: Automatically describe and batch-rename audio files based on their actual sound using local ML or Gemini AI.

Install
cmdop skills install agensi-describe-rename-sound-files

Describe Rename Sound Files (SoundTag AI) is a skill that addresses the problem of cryptic, auto-generated audio filenames by analyzing actual audio content and renaming files with human-readable, descriptive titles following a consistent Title_Case_With_Underscores convention. For example, a filename like audio_track_v2_final_99.wav becomes Bright_Trumpet_Fanfare.wav, and an ElevenLabs-generated file with a timestamp-heavy name becomes Elevenlabs_George_Voice_Speech.mp3.

The skill operates through a two-step workflow. It first runs a local classification using the MIT Audio Spectrogram Transformer (AST), which categorizes sounds into 527 classes — covering Speech, Music, Explosion, and more — entirely offline, avoiding API costs and preserving privacy. For sounds where local classification produces ambiguous results, it makes an improvement pass using the Google Gemini API to generate nuanced descriptions suited to cinematic sound effects, moods, and complex audio textures.

The skill also inspects hints embedded in the original filename so that contextual information already present is not discarded during renaming. Batch processing is supported across .wav, .mp3, .ogg, .flac, .aac, and .m4a formats. Dependency constraints for Torch and Transformers are handled automatically to operate within sandboxed resource limits. The end result is a consistently named, searchable directory of sound files ready for use in sample libraries or field recording archives.

Use cases

  • Batch-rename a disordered sample library so every file has a descriptive, searchable name
  • Clean up auto-generated ElevenLabs or TTS output files with timestamp-heavy filenames
  • Classify field recordings into named categories offline without sending audio to an external API
  • Use Gemini to generate nuanced descriptions for cinematic sound effects and ambient textures
  • Organize foley and SFX archives into a consistent Title_Case_With_Underscores naming scheme
  • Process mixed-format audio collections covering wav, mp3, ogg, flac, aac, and m4a in one pass

When to use it

  • Audio libraries contain auto-generated or timestamp-based filenames that are not human-readable
  • Privacy or cost constraints make sending audio to an external API undesirable for straightforward sounds
  • Files span multiple formats and need uniform naming handled in one batch operation
  • Cinematic SFX or complex ambient recordings need richer descriptions than a basic classifier can provide

When not to use it

  • The goal is audio editing, mixing, or transcription rather than file renaming and organization
  • No local ML runtime is available and no Google Gemini API key is obtainable
  • Audio formats outside the supported set are the primary input
  • The task requires metadata tagging inside audio file headers rather than filename changes