SuperAPI AI Directory

kaipai-video-remove-subtitle

Design & creation

View repository

Updated 10-16 06:46

About this skill

Video subtitle removal

Capabilities and preparation

Always use video-remove-auto to complete video subtitle cleanup; the server automatically identifies the content to be removed and repairs the corresponding picture. When the material and target are clear, execute directly according to existing authorization and keep the original video for comparison; for requirements such as specifying elements to keep or region control, verify the invocation method according to the platform documentation.

Invoke the server-side processing capability through the parameters supported by the current CLI; for specific parameters, consult help or contracts; follow this Skill's automatic removal command binding. Depends on meitu-kaipai-cli, verified target version 0.1.8, compatible with >=0.1.8 <0.2.0。

On first execution, readPlatform access, parse the CLI entry point and check the version and tool video-remove-auto --help. When JSON fields or media restrictions are unclear, consult the platform documentation for kaipai contracts the current tool's entry; when encountering output parsing, server-side inquiries, or execution exceptions, readRunning and recovery。

Collect input

  1. Obtain one real video file or URL from the current request and attachments; do not repeatedly ask when the information is clear. When there are multiple candidates and the target is unclear, ask; do not automatically choose on the user's behalf; when the user has explicitly authorized processing them one by one, invoke separately and record the tasks.
  2. Use a real readable path for local material; for remote material, first followPlatform accessto download the original resource, then upload it as a local file. When only a media ID is available, first query the Task or history of the session it belongs to to obtain the real URL, then download; if that fails, ask the user to download it themselves and provide the local original file.
  3. When continuing an existing task, add -r '<session_id>'; omit the session for a new task. Apply defaults, prepare login, and handle missing input according to the platform documentation; consult the current help for optional parameters, and omit them when unspecified.
  4. Keep the original source, real local path, and session as recovery input. After the user provides the downloaded file, continue with the original target; do not treat failed results as source material.

Upload and submit

Using the parsed CLI entry point, pass the prepared local file as a separate parameter:

kaipai tool video-remove-auto --video-file '<本地视频路径>'

After the CLI validates the file, obtain a proprietary CDN URL through the built-in Meitu upload pipeline, then submit the task and by default wait for this execution to finish. Do not first call create-room / add-media, and do not construct media placeholder text. Parameter files and standalone pre-checks are used only as needed; for safe parameter passing and cleanup rules, see the platform documentation.

Follow-up and delivery

  • Save the original input,session_id / room_url and all real Task IDs; continuously read the original command's stdout and stderr separately; do not open a separate poll at the same time.
  • TASK_STATE_COMPLETED and only deliver the processing result after obtaining a usable artifact URL for this execution. HTTP 200, end of stream, exit code 0, or end.reason=result do not individually prove completion; an unknown task status cannot be regarded as success.
  • Use the host's available native preview/attachment or a complete clickable URL, preserve query parameters, and deliver all available Parts one by one; for partial success, deliver the successful parts first. When there is an actual room_url , attach the Kaipai session entry; do not construct links from IDs.
  • When disconnected, timed out, or acceptance is unknown, first query the original session and task; do not automatically resubmit. Only start a new attempt after the failure cause has been fixed and the user has authorized a retry; if downloading the output artifact fails, only resume the download. For specific inquiry, recovery, and local save steps, see the running instructions.