byted-las-asr-pro

ASR Pro Speech Recognition (las_asr_pro)

Use this Skill when the user wants high-quality speech recognition for audio (including noise reduction, VAD, punctuation, language identification, emotion recognition, speaker separation, etc.).

Notes (⚠️ Must be followed)

• Never let the user enter the 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 The output results of the command are very important and must be fully returned to the user.

Workflow (execute strictly step by step)

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 currently available latest Skill version (las-cli corresponds one-to-one with Skill versions). 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-asr-pro技能, and wait for the installation to complete automatically.
• Authentication check: Prefer the platform identity automatically injected at runtime; if the current environment does not automatically inject it, 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 audio file, upload it to TOS first.

  # 示例: 上传 input.wav
  las-cli tos upload ./input.wav
  # 假设返回 "tos_url": "tos://my-bucket/inputs/xxx.wav"
  

• Prepare parameters: Create params.json, specifying the input and output paths.

  {
    "input_path": "tos://my-bucket/inputs/xxx.wav",
    "output_path": "tos://my-bucket/outputs/asr/"
  }
  

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

las-cli price The output results of the command are very important; do not simplify, modify, or summarize them in any way.

• Calculate price: Must fully return the results output by the following command (in markdown format)

  las-cli price las_asr_pro \
    --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 (⚠️ Directly output the command execution results, do not simplify)

las-cli operators call The output results of the command are very important; do not simplify, modify, or summarize them in any way.

• Execute: Must fully return the results output by the following command (in markdown format)

  las-cli operators call las_asr_pro \
    --params-file ./params.json \
    --format markdown \
    --out ./result.md
  

Step 4: Failure troubleshooting

Keep as is.

• Check task status: las-cli task status <task_id> --operator las_asr_pro
• Check input: Confirm whether the audio format and TOS object exist.
• Check output: Confirm that the output_path directory is writable.
• Check configuration: las-cli config show, confirm authentication and Region.