Tag audio files with genre, mood, energy, tempo, and vocals using offline zero-shot classification.
npx skills add https://github.com/MCERQUA/jam-skills --skill song-tagger
Please help me install this Agent Skill. Skill: song-tagger Source: https://github.com/MCERQUA/jam-skills/tree/main/song-tagger Command: npx skills add https://github.com/MCERQUA/jam-skills --skill song-tagger
This Skill automates the analysis of song structure, providing tags like genre, mood, energy, and tempo to streamline library organization and metadata management.
Run the song-tagger skill on the song 'track.mp3' using the 'song-tagger tag' command.
High-intent search queries and answers about installing and using this skill.
You can automatically tag audio files with genre, mood, energy, tempo, and vocals by running an offline zero-shot classification model. This process batch processes music libraries to fill in missing metadata and improve organization.
The best way to backfill missing metadata for a music library is using automated batch processing. An offline zero-shot classification model analyzes song structures and generates tags like genre and energy to streamline organization.
No, you do not need an internet connection for song tagging because the zero-shot classification model runs entirely offline. Local model execution analyzes audio files and generates metadata tags without external API calls.
Yes, you can batch process audio files for mood and energy tagging. The system is specifically intended for batch processing music libraries, analyzing song structures to output comprehensive metadata tags.
Automated audio analysis determines song structure by using an offline zero-shot classification model to evaluate the audio file. It identifies and categorizes attributes like genre, mood, energy, tempo, and vocals for metadata enhancement.
Filling in music metadata is important for library organization because it significantly improves searchability. Automating this process ensures consistent tags like genre, mood, and tempo are applied across all audio files.
qianleigoodSynthesize Chinese speech offline on Apple Silicon with Qwen3-TTS and MLX models.
ChanghwanKSave Claude conversations as categorized Obsidian Markdown notes with tags and aliases.
nidhalboumaiza-0Transcribe base64-encoded audio into text using the z-ai-web-dev-sdk.
Soul-Brews-StudioParse mood, energy, and trigger fields into a local diary log.
