← 返回 Skills 市场
volcengine-skills

Byted Las Audio Extract And Split

作者 volcengine-skills · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
114
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install byted-las-audio-extract-and-split
功能描述
Extracts audio tracks from video files and splits long audio into timed segments using Volcengine LAS. Audio extraction and separation from video — pull audi...
使用说明 (SKILL.md)

LAS 音频提取与切分(las_audio_extract_and_split

从视频/音频中提取音频轨道并按固定时长切分为多段。支持 mp4/wmv/avi/mkv 等视频格式。

设计模式

本 skill 主要采用:

  • Tool Wrapper:封装 lasutil CLI 调用
  • Pipeline:包含 Step 0 → Step N 的顺序工作流

核心 API 与配置

  • 算子 ID: las_audio_extract_and_split
  • API: 同步(process
  • 环境变量: LAS_API_KEY (必填)

详细参数与接口定义见 references/api.md

Gotchas

  • 路径模板必填output_path_template 必须包含 {index} 变量,否则所有切片会写入同一文件。
  • 密钥安全:若聊天框屏蔽密钥,让用户在当前目录创建 env.sh 并写入 export LAS_API_KEY="...",SDK 会自动读取。
  • 免责声明:最终回复结果时必须包含:"本方式的计费均为预估计费,与实际费用有差距,实际费用以运行后火山产生的账单为准。计费说明请参考 Volcengine LAS 定价。",且禁止使用"实际费用"字眼描述预估价。

工作流(严格按步骤执行)

复制此清单并跟踪进度:

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/提交任务
- [ ] Step 4: 结果呈现

Step 0: 前置检查(⚠️ 必须在第一轮对话中完成)

在接受用户的任务后,不要立即开始执行,必须首先进行以下环境检查:

  1. 检查 LAS_API_KEYLAS_REGION:确认环境变量或 .env 中是否已配置。
    • 若无,必须立即向用户索要(提示:LAS_REGION 常见为 cn-beijing)。
    • 注意LAS_REGION 必须与您的 API Key 及 TOS Bucket 所在的地域完全一致。如果用户中途切换了 Region,必须提醒用户其 TOS Bucket 也需对应更换,否则会导致权限异常或上传失败。
  2. 检查输入路径
    • 如果用户要求处理的是本地文件,则需要先通过 File API 上传至 TOS(只需 LAS_API_KEY,无需额外 TOS 凭证)。
    • 如果算子的输出结果存放在 TOS 上,且用户需要下载回本地,则需要 VOLCENGINE_ACCESS_KEYVOLCENGINE_SECRET_KEY。对于仅需要上传输入文件的场景,TOS 凭证不再必须
  3. 确认无误后:才能进入下一步。

Step 1: 初始化与准备

环境初始化(Agent 必做)

# 执行统一的环境初始化与更新脚本(会自动创建/激活虚拟环境,并检查更新)
source "$(dirname "$0")/scripts/env_init.sh" las_audio_extract_and_split
workdir=$LAS_WORKDIR

如果网络问题导致更新失败,脚本会跳过检查,使用本地已安装的 SDK 继续执行。

  • 处理本地文件时:先本地检查格式和时长,预估价格,用户确认后再上传:
    # 提前检查容器格式(避免参数错误)
    ./scripts/check_format.sh \x3Clocal_path>
    # 本地使用 ffprobe 获取时长(无需上传即可预估价格)
    duration_sec=$(ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:noprint_section=1 \x3Clocal_path>)
    
    计算预估价格并等待用户确认后,再执行上传:
    # 用户确认后,上传到 TOS
    lasutil file-upload \x3Clocal_path>
    
    上传成功后返回 JSON,取其中的 tos_uri(格式 tos://bucket/key)传给算子作为输入路径。

Step 2: 预估价格(⚠️ 必须获得用户确认)

  1. 读取 references/prices.md 获取最新计费标准。
  2. 优先本地获取时长(避免不必要上传):
    # 使用 ffprobe 本地获取
    duration_sec=$(ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:noprint_section=1 \x3Clocal_path>)
    
    如果 ffprobe 失败,再使用 lasutil 远程获取:
    lasutil media-duration \x3Cinput_url>
    
  3. 根据时长和模型单价计算总价,将计费单价与预估总价一并告知用户并强制暂停执行,明确等待用户回复确认。在用户明确回复"继续"、"确认"等同意指令前,绝对禁止进入下一步(执行/提交任务)。提示:预估仅供参考,实际以火山账单为准。计费说明请参考 Volcengine LAS 定价

Step 3: 执行切分 (Process)

构造基础 data.json

{
  "input_path": "\x3Cpresigned_url>",
  "output_path_template": "tos://bucket/output/{index}.wav",
  "split_duration": 30,
  "output_format": "wav"
}

执行命令:

data=$(cat "$workdir/data.json")
lasutil process las_audio_extract_and_split "$data" > "$workdir/result.json"

结果呈现

使用脚本自动生成结果展示(自动包含计费声明):

./scripts/generate_result.md.sh $workdir/result.json \x3Cestimated_price>

生成内容包含:

  • 任务信息卡片
  • 自动生成切分结果表格
  • 自动包含计费声明

手动提取方式:

total=$(jq '.data.output_paths | length' $workdir/result.json)
echo "共 ${total} 个片段"
jq -r '.data.output_paths[] | "  - " + .' $workdir/result.json

审查标准

执行完成后,Agent 应自检:

  1. 环境变量是否正确配置
  2. 输入文件是否成功上传
  3. 输出结果是否正确呈现给用户
  4. 计费声明是否包含
安全使用建议
This skill is plausible for LAS audio splitting but has several inconsistencies and runtime behaviors you should be comfortable with before installing. Things to consider: 1) The SKILL.md and scripts require LAS_API_KEY (and possibly VOLCENGINE access keys and LAS_REGION) and CLI tools (ffprobe, lasutil), yet the registry metadata lists none — ask the author to declare these explicitly. 2) The env_init.sh script downloads a manifest and pip-installs a wheel from a remote URL at runtime; verify that URL and the wheel's integrity (and prefer running this in an isolated VM/container). 3) Do not paste long-lived secrets into chat; avoid committing env.sh with exports into a repo — use short-lived keys and rotate them. 4) If you plan to run this, ensure ffprobe/lasutil are available or the environment can safely install needed binaries, and run the skill in a disposable environment (container) so the pip-installed code and created .las_venv cannot affect other projects. 5) If the publisher cannot explain why metadata omits required env vars and binaries, treat this as an additional red flag and avoid using it with real production credentials.
功能分析
Type: OpenClaw Skill Name: byted-las-audio-extract-and-split Version: 1.0.1 The skill bundle exhibits high-risk behavior by downloading and installing a Python wheel from a remote URL (volces.com) during environment initialization in scripts/env_init.sh, which constitutes a significant supply chain risk. Additionally, SKILL.md instructs the agent to prompt users for sensitive credentials (LAS_API_KEY, VOLCENGINE_ACCESS_KEY/SECRET_KEY) and suggests bypassing chat-based security filters by having the user write these secrets to a local env.sh file. While these actions are functionally aligned with the stated purpose of using Volcengine LAS services, the combination of remote code execution and sensitive credential handling warrants a suspicious classification.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill claims to be an audio-extraction/splitting wrapper for Volcengine LAS, which is plausible, but the package metadata lists no required environment variables or binaries while the SKILL.md and scripts clearly require LAS_API_KEY (and potentially VOLCENGINE_ACCESS_KEY/VOLCENGINE_SECRET_KEY), ffprobe, and the lasutil CLI. Those missing declarations are an incoherence: a genuine integration should declare the required credentials and required binaries.
Instruction Scope
Runtime instructions tell the agent to source scripts/env_init.sh (which fetches a remote manifest and may install a wheel), run ffprobe locally to inspect files, upload local files to TOS via lasutil, and to prompt the user for API keys. The SKILL.md also instructs the user to create an env.sh file containing export LAS_API_KEY — encouraging placement of secrets in the working directory. The instructions access environment variables and external endpoints that were not declared in the skill metadata, and grant the agent broad runtime discretion to perform network installs and uploads.
Install Mechanism
Although there is no declared install spec in the registry, scripts/env_init.sh fetches a manifest from https://las-ai-cn-beijing-online.tos-cn-beijing.volces.com and will pip-install a wheel from that URL at runtime. This runtime network fetch + pip install is effectively installing arbitrary remote code without being declared in the registry metadata. Even if the host is Volcengine-related, an undeclared runtime install is higher-risk and should be explicit and audited.
Credentials
The SKILL.md requires LAS_API_KEY and may require VOLCENGINE_ACCESS_KEY/VOLCENGINE_SECRET_KEY and LAS_REGION, but the skill metadata lists no required env vars. The instructions also tell the user to place API keys in a local env.sh file for automatic reading, which increases the chance of accidental credential leakage. Requesting cloud credentials is reasonable for this integration, but omitting them from the declared requirements and instructing ad-hoc secret placement is disproportionate and confusing.
Persistence & Privilege
always:false (good). The skill creates or reuses a virtualenv (.las_venv) in the project root and creates a temp working directory (LAS_WORKDIR). Creating or reusing a project-level virtualenv is persistent filesystem activity that can affect the host environment; this is expected behavior for runtime setup but should be called out to users (and ideally run in an isolated environment).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install byted-las-audio-extract-and-split
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /byted-las-audio-extract-and-split 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
v1.0.1 highlights a major update to operation flow and documentation, with environment checks, price estimates, and new scripts. - Added workflow checklist and detailed instructions for environment validation, price estimation, and execution before processing tasks. - Introduced scripts for environment initialization, format checking, and consistent result reporting. - Included price reference documentation and evaluation assets. - Changed entrypoint: removed main Python script, now relies on CLI and scripts for all operations. - Strongly emphasizes mandatory price estimate and explicit user confirmation step before job execution. - Improved instructions and clarity on API keys, region matching, and output file path requirements.
v1.0.0
Initial release of byted-las-audio-extract-and-split. - Extract audio from video files (mp4, wmv, etc.) - Split audio into segments of a specified duration - Convert audio formats (wav, mp3, flac) - Supports input and output via TOS - Requires LAS_API_KEY for authentication
元数据
Slug byted-las-audio-extract-and-split
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Byted Las Audio Extract And Split 是什么?

Extracts audio tracks from video files and splits long audio into timed segments using Volcengine LAS. Audio extraction and separation from video — pull audi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 114 次。

如何安装 Byted Las Audio Extract And Split?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install byted-las-audio-extract-and-split」即可一键安装,无需额外配置。

Byted Las Audio Extract And Split 是免费的吗?

是的,Byted Las Audio Extract And Split 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Byted Las Audio Extract And Split 支持哪些平台?

Byted Las Audio Extract And Split 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Byted Las Audio Extract And Split?

由 volcengine-skills(@volcengine-skills)开发并维护,当前版本 v1.0.1。

💬 留言讨论