Skip to content
Agentmart
Submit a tool

byted-vod-process-tools

Volcengine VOD audio and video processing tools skill.

Skill by bytedanceOfficial

IndexedApache-2.0★ 473
Write a review

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-vod-process-tools

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

Volcengine VOD audio and video processing tools skill. Use when users need VOD-based media processing or editing: upload local/URL media, stitch videos, trim clips, flip frames, change playback speed, create image-to-video, compose audio/video, extract audio, mix audio, separate vocals/accompaniment, denoise audio, enhance quality, AI super-resolution, frame interpolation, ASR speech-to-text, OCR text extraction, subtitle removal, subtitle embedding, scene slicing, portrait/green-screen matting, highlight extraction, comic style transfer, video translation, drama recap narration, drama script restoration, media info lookup, or playback URL retrieval. The skill submits async VOD jobs, polls task status, and returns generated output links. Not for pure text generation, real-time streaming, or source-free generative video creation.

Use cases: ml, 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-vod-process-tools

What's inside

Skill name
byted-vod-process-tools
Description
Volcengine VOD audio and video processing tools skill. Use when users need VOD-based media processing or editing: upload local/URL media, stitch videos, trim clips, flip frames, change playback speed, create image-to-video, compose audio/video, extract audio, mix audio, separate vocals/accompaniment, denoise audio, enhance quality, AI super-resolution, frame interpolation, ASR speech-to-text, OCR text extraction, subtitle removal, subtitle embedding, scene slicing, portrait/green-screen matting, highlight extraction, comic style transfer, video translation, drama recap narration, drama script restoration, media info lookup, or playback URL retrieval. The skill submits async VOD jobs, polls task status, and returns generated output links. Not for pure text generation, real-time streaming, or source-free generative video creation.
License
Apache-2.0
Metadata
version: 1.0.5 · display_name: 火山引擎 VOD 音视频处理工具集
Instructions
229 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (68)

  • LICENSE
  • SKILL.md
  • 00-billing-instructions.md · references/
  • 01-stitching.md · references/
  • 02-clipping.md · references/
  • 03-flip.md · references/
  • 04-speedup.md · references/
  • 05-image-to-video.md · references/
  • 06-compile.md · references/
  • 07-extract-audio.md · references/
  • 08-mix-audios.md · references/
  • 09-add-sub-video.md · references/
  • 10-voice-separation.md · references/
  • 11-noise-reduction.md · references/
  • 12-quality-enhance.md · references/
  • 13-super-resolution.md · references/
  • 14-interlacing.md · references/
  • 15-asr-speech-to-text.md · references/
  • 16-ocr-text-extract.md · references/
  • 17-subtitle-removal.md · references/
  • 18-add-subtitle.md · references/
  • 19-intelligent-slicing.md · references/
  • 20-portrait-matting.md · references/
  • 21-green-screen.md · references/
  • 22-comic-style.md · references/
  • 23-highlight.md · references/
  • 24-video-translation.md · references/
  • 25-drama-recap.md · references/
  • 26-drama-script.md · references/
  • 27-get-media-info.md · references/
  • add_subtitle.py · scripts/
  • api_manage.py · scripts/
  • asr_speech_to_text.py · scripts/
  • clipping.py · scripts/
  • comic_style.py · scripts/
  • compile.py · scripts/
  • drama_recap.py · scripts/
  • drama_script.py · scripts/
  • extract_audio.py · scripts/
  • flip.py · scripts/
  • get_media_info.py · scripts/
  • green_screen.py · scripts/
  • highlight.py · scripts/
  • image_to_video.py · scripts/
  • intelligent_slicing.py · scripts/
  • interlacing.py · scripts/
  • list_translation.py · scripts/
  • log_utils.py · scripts/
  • mix_audios.py · scripts/
  • noise_reduction.py · scripts/
  • ocr_text_extract.py · scripts/
  • poll_media.py · scripts/
  • poll_translation.py · scripts/
  • poll_vcreative.py · scripts/
  • portrait_matting.py · scripts/
  • quality_enhance.py · scripts/
  • speedup.py · scripts/
  • stitching.py · scripts/
  • subtitle_removal.py · scripts/
  • super_resolution.py · scripts/
  • …and 8 more

SKILL.md (first lines)

# Volcengine VOD Tools

---

## 前置条件

- **Python**:确认 `python --version` ≥ 3.6
- **环境变量**(必需,也可通过工作目录下的 `.env` 文件配置,脚本会自动加载):
  - `VOLCENGINE_ACCESS_KEY` — 火山引擎 Access Key
  - `VOLCENGINE_SECRET_KEY` — 火山引擎 Secret Key
  - `VOD_SPACE_NAME` — VOD 空间名称
- **依赖**:脚本依赖 `python-dotenv`

---

## 参数传入方式

所有脚本支持两种 JSON 参数传入方式:

1. **内联 JSON**(适合简单参数):`python script.py '{"key":"value"}'`
2. **文件引用**(推荐,避免 shell 转义问题):`python script.py @params.json`

`@` 前缀表示从文件读取 JSON 内容,文件路径相对于当前工作目录。

---

## 结果交付规则
- 提交异步任务成功后会返回异步任务id,字段为 `VCCreativeId` 或 `TaskId`,在给用户交付最终产物时,**必须**包含异步任务id
- 在展示最终产物链接时,**禁止**随意修改链接内容
- **优先**将产物链接提供给用户
---

## 工作流程

### 1) 识别输入视频类型(必要时先上传拿 `vid://...`)

后续所有处理脚本**优先使用 VOD 侧资源引用**:

- Vid:`vid://vxxxx`(或部分脚本接受裸 `vxxxx` 并自动补 `vid://`)
- DirectUrl / FileName:`directurl://<vod_file_name>`(媒体类任务用 `DirectUrl` 时会要求 `FileName + SpaceName`)

当用户提供的是以下输入之一,需要先执行上传逻辑,拿到 `Vid` 后再继续:

- 本地文件路径:如 `/path/to/a.mp4`
- `http/https` 链接:如 `https://example.com/a.mp4`(会走 URL 拉取上传,并轮询上传结果)

统一用 `scripts/upload_media.py`:

```bash
python <SKILL_DIR>/scripts/upload_media.py "<local_file_path_or_http_url>" [space_name]
```

脚本输出中 `Source` 字段即 `vid://...`,可直接作为后续处理输入。

> **安全限制**:本地文件上传仅允许 workspace/、userdata/ 和 /tmp 目录下的文件。

### 2) 识别用户意图 → 选择对应处理脚本

根据用户需求,按以下决策树选择脚本:

| 用户意图 | 脚本 |
|---|---|
| 多个视频/音频合成一个(顺序拼接) | `stitching` |
| 截取视频/音频的某个时间片段 | `clipping` |
| 加速/慢放/变速 | `speedup` |
| 镜像/上下翻转/左右翻转 | `flip` |
| 多张图片串联生成视频 | `image_to_video` |
| 替换/叠加视频的背景音乐 | `compile` |
| 只要视频里的音频轨 | `extract_audio` |
| 多条音频同时叠加播放(混音) | `mix_audios` |
| 分离人声和伴奏/背景音 | `voice_separation` |
| 去除环境噪音/电流杂音/风噪 | `noise_reduction` |
| 模糊/低画质视频修复(压缩伪影/噪点/划痕) | `quality_enhance` |
| 低分辨率视频提升(如 720P→1080P) | `super_resolution` |
| 低帧率视频插帧提升流畅度(如 30fps→60fps) | `interlacing` |
| 语音识别/ASR/提取视频中的文字对白 | `asr_speech_to_text` |
| OCR 文字提取/识别视频中的屏幕文字 | `ocr_text_extract` |
| 擦除视频硬字幕 | `subtitle_removal` |
| 给视频添加/嵌入字幕(烧录字幕) | `add_subtitle` |
| 视频场景分割/智能切片 | `intelligent_slicing` |
| 人像抠图/人像分割 | `portrait_matting` |
| 绿幕抠像/绿屏抠像 | `green_screen` |
| AI 漫剧转绘(漫画风/3D卡通风格) | `comic_style` |
| 短剧高光剪辑/精彩片段提取 | `highlight` |
| AI 视频翻译(字幕/语音/面容翻译) | `video_translation` |
| 查询翻译项目状态/重启翻译轮询 | `poll_translation` |
| 查询翻译项目列表 | `list_translation` |
| AI 解说视频生成(短剧解说/二创) | `drama_recap` |
| AI 剧本还原(视频转结构化剧本) | `drama_script` |
| 查询媒资信息(Vid 详情+播放地址) | `get_media_info` |

### 3) 构造参数并执行

#### 视频编辑类

| 脚本 | 用途 | 详细参数 |
|------|------|---------|
| `stitching.py '<json>'` | 视频/音频拼接 | [references/01-stitching.md](references/01-stitching.md) |
| `clipping.py '<json>'` | 视频/音频裁剪 | [references/02-clipping.md](references/02-clipping.md) |
| `flip.py '<json>'` | 视频翻转 | [references/03-flip.md](references/03-flip.md) |
| `speedup.py video '<json>'` | 视频变速 | [references/04-speedup.md](references/04-speedup.md) |
| `speedup.py audio '<json>'` | 音频变速 | [references/04-speedup.md](references/04-speedup.md) |
| `image_to_video.py '<json>'` | 图片转视频 | [references/05-image-to-video.md](references/05-image-to-video.md) |
| `compile.py '<json>'` | 音视频合成 | [references/06-compile.md](references/06-compile.md) |
| `extract_audio.py '<json>'` | 提取音轨 | [references/07-extract-audio.md](references/07-extract-audio.md) |
| `mix_audios.py '<json>'` | 混音 | [references/08-mix-audios.md](references/08-mix-audios.md) |

#### 媒体处理类

| 脚本 | 用途 | 详细参数 |
|------|------|---------|
| `voice_separation.py '<json>'` | 人声分离 | [references/10-voice-separation.md](references/10-voice-separation.md) |
| `noise_reduction.py '<json>'` | 音频降噪 | [references/11-noise-reduction.md](references/11-noise-reduction.md) |
| `quality_enhance.py '<json>'` | 综合画质修复 | [references/12-quality-enhance.md](references/12-quality-enhance.md) |
| `super_resolution.py '<json>'` | AI 超分辨率 | [references/13-super-resolution.md](references/13-super-resolution.md) |
| `interlacing.py '<json>'` | 智能补帧 | [references/14-interlacing.md](references/14-interlacing.md) |

#### AI 内容分析类

From bytedance/agentkit-samples, Apache-2.0.

More from bytedance/agentkit-samples

Signals

Stars
473
Forks
101
Open issues
14
Last commit (this folder)
May 6, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0.5
License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from bytedance

Cite this page

byted-vod-process-tools skill. Agent Mart. https://agentmart.dev/skills/bytedance-byted-vod-process-tools (last updated 2026-10-24)