SuperAPI AI Directory

byted-las-audio-extract-and-split

General & other

View repository

Updated 10-15 17:30

About this skill

Audio Extraction and Splitting (las_audio_extract_and_split)

Use this Skill when the user needs to extract audio tracks from videos or split long audio by rules (such as duration, silence).

Notes (⚠️ Must be followed)

  • Never ask the user to enter AccessKey and SecretKey.
  • Files can only be downloaded using the las-cli tos download command (compatible with both tos and non-tos resources).
  • las-cli operators call and las-cli price command outputs are very important and must be returned to the user in full.

Workflow (Follow the steps strictly)

Copy this checklist and track progress:

执行进度:
- [ ] Step 0: 前置检查
- [ ] Step 1: 初始化与准备
- [ ] Step 2: 预估价格
- [ ] Step 3: 执行任务并呈现结果
- [ ] Step 4: 失败排查

Step 0: Pre-checks

Version check (required): Please run las-cli install 0.3.8. If the las-cli command does not exist, run npm i -g "@volcengine/las-cli@0.3.8"

  • New version reminder: Please run npm info @volcengine/las-cli version to check the latest available Skill version (las-cli corresponds one-to-one with the Skill version). If the returned version is higher than the version marked for this Skill, first prompt the user to upgrade the current Skill. Upgrade method: ask the user to send the natural language instruction 帮我安装byted-las-audio-extract-and-split技能, then wait for the installation to complete automatically.
  • Authentication check: Prefer the platform identity automatically injected at runtime; if the current environment does not inject it automatically, then run las-cli config show to confirm that the legacy credentials las.apiKey and volcengine.region are configured.

Step 1: Initialization and Preparation

  • Upload resources: If the input is a local media file, first upload it to TOS.
    las-cli tos upload ./input.mp4
    # 假设返回 "tos_url": "tos://my-bucket/inputs/xxx.mp4"
    
  • Prepare parameters: Create params.json, specify the input, output, and splitting strategy, and note that output_path should include a unique identifier to avoid overwriting existing files.
    {
      "input_path": "tos://my-bucket/inputs/xxx.mp4",
      "output_path": "tos://my-bucket/outputs/audio_split/",
      "split_mode": "duration",
      "split_duration": 60
    }
    

Step 2: Estimate Price (⚠️ Must obtain user confirmation)

las-cli price The command output is very important; do not simplify, modify, or summarize it in any way.

  • Calculate price: Must fully return the output of the following command (in markdown format)
    las-cli price las_audio_extract_and_split \
      --params-file ./params.json \
      --format markdown
    
  • User confirmation: After outputting the estimated price,must wait for user confirmation。

Step 3: Execute the task and present the results (⚠️ Output the command execution results directly, do not simplify)

las-cli operators call The command output is very important; do not simplify, modify, or summarize it in any way.

  • Execute: Must fully return the output of the following command (in markdown format)
    las-cli operators call las_audio_extract_and_split \
      --params-file ./params.json \
      --format markdown \
      --out ./result.md
    

Step 4: Troubleshooting

Keep as is.

  • Check input/output: Confirm whether the TOS path exists, is readable, and is writable.
  • Check configuration: las-cli config show。
  • View help: las-cli operators help las_audio_extract_and_split, check the splitting parameters.