CORPUS Intelligence active
Sofilab GmbH (CORPUS) vunknown added 2026-05-29 verified 2026-06-19
You need to find music using natural language descriptions instead of tag-based searches across 40,000+ CC-BY licensed tracks.
about
CORPUS Intelligence is a semantic music search and exploration tool that matches tracks against dense natural-language descriptions in embedding space rather than relying on traditional tag-based taxonomy. The system accepts text descriptions, reference audio files, or images as query inputs, enabling users to search for music based on mood, scene context, sonic characteristics, or conceptual ideas.
The platform indexes over 40,000 Creative Commons (CC-BY) licensed tracks and uses AI-powered semantic understanding to retrieve musically relevant results. This approach allows for more intuitive and flexible music discovery compared to conventional keyword or metadata filtering systems.
related
SFX Stacks
StandaloneSFX Stacks is a desktop application that uses AI to search local sound effects libraries with natural language queries. It combines semantic search with similarity-based discovery, allowing you to find sounds by description then explore similar variations from any result or reference file. The tool indexes your existing library locally and provides integrated preview, waveform editing, and export capabilities in a single interface. Unlike cloud-based solutions, all processing happens on your machine—your library stays local. The similarity search feature lets you use any found result or dropped reference file as a starting point to discover related sounds you wouldn't have thought to search for directly. This workflow reduces the time spent manually browsing folders or clicking through near-matches. The application runs on Windows 10/11 and macOS (Apple Silicon) and works with your existing file organization. No restructuring or uploading required. A free tier (limited results, no account) is available, with a one-time Pro purchase unlocking the full library size.
wwise-control
Wwisewwise-control is a Claude Code skill and Python helper module that connects an AI agent to Wwise over the Wwise Authoring API (WAAPI). You describe what you want in plain language — creating containers, setting routing, adjusting properties, generating SoundBanks — and the agent translates that into pywwise calls without you writing or running scripts yourself. The package ships two files: a Python module (`wwise_for_claude.py`) that wraps pywwise with tested helpers for finding, creating, moving, renaming, and routing objects; and a SKILL.md that documents non-obvious WAAPI/WAQL quirks discovered through live testing (e.g. object identity requires `.guid` not `.id`, purely-numeric Bus names are rejected by Wwise). The skill instructs the agent to probe before writing, wrap batch edits in a Wwise undo group, verify results after each write, and confirm before deleting. Intended for use on version-controlled projects.