Usage Rules
- First read
../byted-mediakit-shared/SKILL.md, and perform the unified pre-check; if this Skill is missing, stop and prompt for installation. - Only select from the table below the
audiodomain tools; similar capabilities are distinguished by each tool's "capability description" and parameter boundaries. - Before execution, read the corresponding reference as needed; parameter and result descriptions come from the same reviewed copy, and the complete machine contract is subject to the current CLI
--schema. - When required parameters, authentication environment variables, or real input resources are missing, ask the user for them; generic optional fields may only pass through values explicitly provided by the user, while other optional fields may be accurately determined from clear intent, but must not be fabricated.
- At execution time, set
MEDIAKIT_SURFACE=skill, specifying that the invocation source is Skill. - At execution time, set
MEDIAKIT_RUNTIMEto the current Agent host, to avoid the CLI being unable to reliably identify the parent Agent.
Clarification and Cross-Domain Routing
If it is only said that there is audio without stating the business objective, clarification should be made first. Editing and compositing requests such as audio trimming, concatenation, speed adjustment, fade in/out, mixing, extracting audio tracks from video, or audio-video merging should be routed to editing; subtitle generation, subtitle extraction, speech-to-subtitle, video understanding, video enhancement, etc. should be routed to video.
Tool List
| Tool | Description | Supported Modes | Command | Reference |
|---|---|---|---|---|
| detect-voice-activity | Used for speech endpoint detection. Automatically locates the start and end times of valid speech in audio or video files. Distinguishes human speech from invalid segments such as silence and background noise. Returns a list containing the start and end timestamps of all valid speech segments. | Cloud | mediakit-cli audio detect-voice-activity |
reference/detect-voice-activity.md |
| probe-audio-metadata | Detects the input audio URL and outputs standardized media asset metadata, used to obtain audio metadata. | Cloud / Local | mediakit-cli audio probe-audio-metadata |
reference/probe-audio-metadata.md |
| separate-voice | Used for vocal/background sound separation, it can precisely separate vocals from background sound in audio or video files, outputting two independent audio files. | Cloud | mediakit-cli audio separate-voice |
reference/separate-voice.md |
| transcode-audio | Audio transcoding converts one audio bitstream into another audio bitstream, usually involving conversion of encoding format, encoding parameters, and encapsulation format, used to adapt to different business scenarios, playback terminals, and network environments. | Cloud | mediakit-cli audio transcode-audio |
reference/transcode-audio.md |