Skip to content
Agentmart
Submit a tool

byted-mediakit-voiceover-editing

Volcano Engine AI MediaKit talking-head video editing Skill: a one-stop workflow from environment setup through media management, audio processing…

Skill by bytedanceOfficial

IndexedApache-2.0★ 473
Write a review

Chalk Labs

Need help deploying byted-mediakit-voiceover-editing?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bytedance-byted-mediakit-voiceover-editing

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Volcano Engine AI MediaKit talking-head video editing Skill: a one-stop workflow from environment setup through media management, audio processing, talking-head cuts, video export, review UI, and iterative refinement. You MUST invoke this Skill when the user mentions talking-head editing, cutting talking video, video editing, removing pauses, processing audio, exporting talking video, automatic editing, removing verbal slips, or similar. Also invoke when the user uploads video or audio and asks for editing.

Use cases: design, writing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/byted-mediakit-voiceover-editing

What's inside

Skill name
byted-mediakit-voiceover-editing
Description
Volcano Engine AI MediaKit talking-head video editing Skill: a one-stop workflow from environment setup through media management, audio processing, talking-head cuts, video export, review UI, and iterative refinement. You MUST invoke this Skill when the user mentions talking-head editing, cutting talking video, video editing, removing pauses, processing audio, exporting talking video, automatic editing, removing verbal slips, or similar. Also invoke when the user uploads video or audio and asks for editing.
License
Apache-2.0
Instructions
214 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (60)

  • LICENSE
  • README.md
  • SKILL.md
  • edl.json · examples/
  • step6_speech_cut.json · examples/
  • track_witdh_request.json · examples/
  • web-sdk.js · examples/
  • ASR语义纠错.md · references/内置/
  • EDL编辑决策格式.md · references/内置/
  • 目标平台配置.md · references/内置/
  • 1. 环境检查.md · references/执行步骤/
  • 2. 语气词提示与用户行为更新.md · references/执行步骤/
  • 3. URL到ASR流水线与候选生成.md · references/执行步骤/
  • 4. ASR语义纠错.md · references/执行步骤/
  • 5. 口播剪辑.md · references/执行步骤/
  • 5.5 审核逻辑确认.md · references/执行步骤/
  • 6a. 数据预处理.md · references/执行步骤/
  • 6b. 审核与导出.md · references/执行步骤/
  • 6c. VOD导出任务提交与查询.md · references/执行步骤/
  • 1-核心原则.md · references/用户规则/
  • 10-顺句词删除.md · references/用户规则/
  • 2-语气词检测.md · references/用户规则/
  • 3-静音段处理.md · references/用户规则/
  • 4-重复句检测.md · references/用户规则/
  • 5-卡顿词.md · references/用户规则/
  • 6-句内重复检测.md · references/用户规则/
  • 7-连续语气词.md · references/用户规则/
  • 8-重说纠正.md · references/用户规则/
  • 9-残句检测.md · references/用户规则/
  • README.md · references/用户规则/
  • 变更记录.md · references/用户规则/
  • api_manage.py · scripts/
  • apply_review_to_export.py · scripts/
  • asr_volc.py · scripts/
  • execution_mode.py · scripts/
  • export_server.py · scripts/
  • ffmpeg_utils.py · scripts/
  • local_asr.py · scripts/
  • local_av_separation.py · scripts/
  • local_denoise.py · scripts/
  • local_export.py · scripts/
  • local_media_ops.py · scripts/
  • local_subtitle.py · scripts/
  • merge_asr_words.py · scripts/
  • output_dir_resolve.py · scripts/
  • pipeline_url_to_asr.py · scripts/
  • prepare_export_data.py · scripts/
  • project_paths.py · scripts/
  • requirements-local.txt · scripts/
  • requirements.txt · scripts/
  • serve_review_page.py · scripts/
  • setup.sh · scripts/
  • step2_confirm_config.py · scripts/
  • track_cut_realign.py · scripts/
  • vod_direct_export.py · scripts/
  • vod_local_upload.py · scripts/
  • vod_transport.py · scripts/
  • volc_request.py · scripts/
  • env.md · templates/
  • index.html · templates/review-page/

SKILL.md (first lines)

## 一、模式与凭据

### 1.1 三种执行模式

| 模式      | 说明                                 | 所需环境变量                                                                                               | ASR 方式           |
| --------- | ------------------------------------ | ---------------------------------------------------------------------------------------------------------- | ------------------ |
| **apig**  | SkillHub 网关代理,Bearer Token 认证 | `ARK_SKILL_API_BASE` + `ARK_SKILL_API_KEY`(容器注入)+ `VOLC_SPACE_NAME` + `ASR_API_KEY` + `ASR_BASE_URL` | 豆包语音大模型     |
| **cloud** | 直连火山引擎 OpenAPI,HMAC 签算      | `VOLC_ACCESS_KEY_ID` + `VOLC_ACCESS_KEY_SECRET` + `VOLC_SPACE_NAME` + `ASR_API_KEY` + `ASR_BASE_URL`       | 豆包语音大模型     |
| **local** | 完全本地执行,无需云端服务           | 无(可选 `EXECUTION_MODE=local`)                                                                          | Qwen3-ASR 本地推理 |

**优先级**:`apig > cloud > local`。自动检测按此顺序依次检查环境变量,缺参时打印 `.env` 路径与缺失变量列表并自动降级。

### 1.2 凭据配置

- **`.env` 文件位置**:`<SKILL_DIR>/.env`
- 脚本先读**进程环境变量**,再用 `.env` **补全未设置的项**(不覆盖容器注入)
- `ARK_SKILL_*` 通常由部署容器注入,**不必**手写到 `.env`
- **缺参不阻塞**:不使用终端 `input()` 交互,缺参时打印提示信息并自动降级到可用模式
- Agent 推荐用户通过**编辑 `.env` 文件**或**Agent 文件写入工具**来配置变量,避免终端粘贴问题
- **安全**:控制台创建**仅含所需权限**的密钥;测试请用**独立点播空间**;`.env` 勿提交仓库

### 1.3 模式意图识别(Agent 必读)

当用户在对话中表达模式切换意图时,Agent 应识别并执行:

| 用户表达                               | 识别为                 | 操作                            |
| -------------------------------------- | ---------------------- | ------------------------------- |
| "用本地模式" / "不走云端" / "离线处理" | `EXECUTION_MODE=local` | 写入 `.env` 或传 `--mode local` |
| "用云端" / "用火山引擎" / "走 AK/SK"   | `EXECUTION_MODE=cloud` | 写入 `.env` 或传 `--mode cloud` |
| "走网关" / "用 apig" / "用 SkillHub"   | `EXECUTION_MODE=apig`  | 写入 `.env` 或传 `--mode apig`  |

**隔离要求**:各任务的模式选择相互独立。一个任务中切换到 local 不应影响另一个任务的模式。Agent 应在每次任务开始时重新检测或遵循用户当次指定。

---

## 二、执行约束(STRICT — NO EXCEPTIONS)

1. **仅使用以下脚本**,禁止创建新脚本
2. **按顺序执行所有步骤**,跳步即任务失败
3. 执行任何脚本前必须先 `cd <SKILL_DIR>/scripts`
4. 每个 CHECKPOINT 必须验证产物后再继续
5. 任何步骤失败必须**立即停止并报告**,不得继续
6. Step 4/5/6 输出**禁止**简化版、占位符、示例或省略内容
7. **最终输出必须保持原样,不能做任何修改**
8. 审核页是否自动打开由 `TALKING_VIDEO_AUTO_EDIT_REVIEW_AUTO_OPEN` 决定(**强制**):Agent 不得额外执行 `open`/`start`/`xdg-open` 等命令
9. **超时设置**:音视频处理时长较长,宿主超时时间应设置为 **60 分钟**

### 职责分工

| 组件                 | 职责                                                | 不做                  |
| -------------------- | --------------------------------------------------- | --------------------- |
| **脚本(规则引擎)** | ASR 优化、候选生成(标记位置+规则置信度+删除建议)  | 不做最终删除/保留决策 |
| **宿主 Agent(你)** | 语义断句、口癖识别确认、候选复核、最终删除/保留决策 | 不修改脚本            |

**核心原则:脚本提供候选(含 deleted_parts + cleaned_text),Agent 做最终决策。**

---

## 三、路径规则

### 3.1 SKILL_DIR 与 Output-dir

- **SKILL_DIR**:`byted-mediakit-voiceover-editing` 目录路径
- **PROJECT_ROOT**:由 `scripts/project_paths.py` 推导:
  1. 环境变量 `VOICEOVER_EDITING_PROJECT_ROOT` 若设置则用之
  2. 否则为 `<SKILL_DIR>` 的 `parents[2]`(沿父链上移 3 级,不依赖中间目录命名)
- **Output-dir**:`<PROJECT_ROOT>/output/<素材名>/`;若目录已存在则自动递增为 `<素材名>_01`、`<素材名>_02`...
- 脚本启动时会打印路径推导日志,便于调试确认

### 3.2 素材名推导

| 来源      | 推导规则             | 示例                                            |
| --------- | -------------------- | ----------------------------------------------- |
| URL       | 取最后一段去扩展名   | `https://x.com/video.mp4` → `video`             |
| 本地文件  | 取文件名去扩展名     | `/path/Test_Video_720p.mp4` → `Test_Video_720p` |
| DirectUrl | 取 FileName 去扩展名 | `test.mp4` → `test`                             |
| Vid       | 取 Vid 值            | `v0xxx` → `v0xxx`                               |

### 3.3 从上下文推导 output-dir

- **推导优先级**(按顺序尝试):
  1. 对话历史/命令参数中已显式传入 `--output-dir output/<子目录>` → 直接沿用
  2. 无法从对话历史获得 → 询问用户指定
- Agent **不得**扫描仓库来推断 `output-dir`

### 3.4 重复处理

写入任何输出文件/目录前,若目标已存在,**必须提示用户**:

- 目录已存在:「是否删除原目录?[删除/保留并新建(01)]」
- 文件已存在:「是否删除/覆盖/保留?」
- 超时 20 秒默认「保留并新建(01)」

---

## 四、脚本清单

> 执行前必须 `cd <SKILL_DIR>/scripts`

| 脚本                                | 用途                                                        |
| ----------------------------------- | ----------------------------------------------------------- |
| `./scripts/setup.sh`                | 环境检查与依赖安装                                          |
| `./scripts/step2_confirm_config.py` | Step 2: 语气词/卡顿词确认完成后生成 checkpoint(阻止跳步)  |
| `./scripts/pipeline_url_to_asr.py`  | Step 3: URL → ASR 流水线(支持 `--mode local/cloud/apig`)  |
| `./scripts/merge_asr_words.py`      | Step 4 产出缺 words 时,从 raw 合并                         |
| `./scripts/prepare_export_data.py`  | Step 6a: 数据预处理(`--width` `--height` `--write-step6`) |
| `./scripts/serve_review_page.py`    | Step 6b: 审核页静态服务 + 数据保存 + 导出代理               |
| `./scripts/export_server.py`        | 导出服务(独立进程,接收审核页 POST)                       |
| `./scripts/vod_direct_export.py`    | Step 6c: VOD 导出任务提交与查询                             |

---

## 五、必经步骤

> **执行顺序**:按顺序执行所有步骤,不得跳步即任务失败
> 各 Step 完整检查单见 `references/执行步骤/` 下分步文档。

| Step     | 说明                        | 文档                                                                                   |
| -------- | --------------------------- | -------------------------------------------------------------------------------------- |

From bytedance/agentkit-samples, Apache-2.0.

More from bytedance/agentkit-samples

Signals

Stars
473
Forks
101
Open issues
14
Last commit (this folder)
Apr 30, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from bytedance

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get byted-mediakit-voiceover-editing running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying byted-mediakit-voiceover-editing?

CallGet help
Cite this page

byted-mediakit-voiceover-editing skill. Agent Mart. https://agentmart.dev/skills/bytedance-byted-mediakit-voiceover-editing (last updated 2026-10-24)