byted-mediakit-audio
ZHYour audio, with voices and background separated.
What it does
Processes audio or video soundtracks into speech timestamps, metadata, separated voice and background tracks, or converted audio.
When to use it
Use for speech boundary detection, audio metadata inspection, transcoding, or voice separation, including when the audio goal is clear but the method is not.
How to use it
Give it an audio or video source and a processing request; it returns speech timestamps, metadata, or links to processed audio.
What you provide
- an audio or video URL or path
Uses
What you need · 3
Requires the mediakit-cli binary to call the audio processing commands.
Requires the shared skill for preliminary checks; stops and asks for installation if it is missing.
Requires authentication environment variables and asks the user when they are missing; these files do not name the variables.
Access · 1
This skill
AI MediaKit
Starts cloud audio processing jobs
Sends media sources to MediaKit