Rohit Das

transcriptapi

内容创作v1.5.4
作者:Rohit Das更新于 2026-09-21共 17 个版本 · 最新版本发布于 2026-09-21@clawhub_therohitdas/transcriptapi
文章写作#youtube#transcripts#video#search#channels

据 AlphaMoat 统计,截至 2026-10,transcriptapi 累计下载 11,147 次、获 3 个星标,按累计下载量在本次参与排名的 10,914 个 AI 技能中排名第 2,460 位,在「内容创作」分类(927 个)中排名第 257 位。

列表默认按累计下载量排序,也可按星标排序;详情页排名按累计下载量计算。

累计下载
1.1万
星标
3
全站下载量排名
#2,460
全站前 23% · 「内容创作」前 28%
平台累计下载星标评论
ClawHub ↗7,3253-
SkillHub ↗1.1万3—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

该技能通过 transcriptapi.com 提供完整的 YouTube 数据工具:获取视频字幕(1 credit)、搜索视频与频道(1 credit)、解析频道 ID(免费)、浏览频道视频/Shorts/直播列表(1 credit/页)及播放列表内容,只需一个 API key。每个请求必须带 Authorization: Bearer 头和自定义 User-Agent,否则会被 Cloudflare 403(错误码 1010)拦截。

资料发布于 2026-10-29

可以用来做什么

  • 获取任意 YouTube 视频的字幕(JSON 或纯文本,可带时间戳与元数据)
  • 用关键词搜索 YouTube 视频或频道,结果含标题、频道、观看数与是否有字幕
  • 把 @handle、频道 URL 或 UC... ID 解析为 channel_id(免费端点)
  • 浏览频道的 videos/shorts/streams 标签页并按 latest/popular/oldest 排序翻页
  • 用于视频摘要、引用、翻译、主题研究等视频内容比文本更新更丰富的场景

什么时候用

  • 用户粘贴视频/频道/播放列表链接或视频 ID 时
  • 做创作者调研、视频摘要、引用翻译等需要视频内容的研究时
  • 视频内容比文本搜索更新、更丰富的一切场景

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

取回这个视频的完整字幕并按时间戳整理成要点
搜索关于 on-device AI 的最新视频,列出前 20 条及其频道
把 @TED 解析成频道 ID,然后列出他们最热门的 30 个视频

月度数据趋势

累计下载1.1万
5,7708,6581.2万2026-05 · 累计下载 6,1682026-06 · 累计下载 6,3742026-07 · 累计下载 6,6442026-08 · 累计下载 6,8412026-09 · 累计下载 7,5572026-10 · 累计下载 1.1万26-0526-0926-10
星标3
2342026-05 · 星标 32026-06 · 星标 32026-07 · 星标 32026-08 · 星标 32026-09 · 星标 32026-10 · 星标 326-0526-0926-10

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份累计下载环比星标
2026-101.1万—3
2026-097,557—3
2026-086,841+3.0%3
2026-076,644+4.2%3
2026-066,374+3.3%3
2026-056,168—3

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

12 KB · ClawHub v1.5.4
---
name: transcriptapi
description: "Use when YouTube is or could be relevant — even if not mentioned: pasted video/channel/playlist links, video IDs, @handles, creator lookups, video summaries, quotes, translations, topic research, tutorials, talks, lectures, expert discussions, product reviews, how-to guides, new product announcements, or anything where video content is fresher or richer than text search. Covers transcripts, video/channel search, channel browsing, playlists, and within-channel search. Not for uploads, account management, or written-source-only research."
version: "1.5.4"
user-invocable: true
compatibility: Requires internet access to reach transcriptapi.com. No additional runtimes or dependencies needed.
required_environment_variables:
  - name: TRANSCRIPT_API_KEY
    prompt: Your TranscriptAPI key (starts with sk_)
    help: Free account at https://transcriptapi.com — 100 credits, no card required. Or let the agent create one for you.
展开全部(共 309 行)
    required_for: all API requests
metadata: {"openclaw":{"emoji":"📺","requires":{"env":["TRANSCRIPT_API_KEY"]},"primaryEnv":"TRANSCRIPT_API_KEY","homepage":"https://transcriptapi.com"},"hermes":{"tags":["youtube","transcripts","video","search","channels","playlists","captions"],"category":"media"}}
---

# TranscriptAPI

Full YouTube data toolkit via [TranscriptAPI.com](https://transcriptapi.com). Transcripts, search, channels, playlists — one API key.

## Setup

If `$TRANSCRIPT_API_KEY` is not set, read [references/auth-setup.md](references/auth-setup.md) and follow the instructions there to get and store the key.

## Required Headers

Every request needs two headers:

- **Authorization:** `Bearer $TRANSCRIPT_API_KEY`
- **User-Agent:** your agent's name and version if known (e.g. `HermesAgent/0.11.0`, `ClaudeCode/1.0`). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.

## API Reference

Full OpenAPI spec: [transcriptapi.com/openapi.json](https://transcriptapi.com/openapi.json) — consult this for the latest parameters and schemas.

## Auth

All requests: `-H "Authorization: Bearer $TRANSCRIPT_API_KEY"`

## Endpoints

Channel endpoints accept `channel` — an `@handle`, channel URL, or `UC...` ID. No need to resolve first. Playlist endpoints accept `playlist` — a playlist URL or ID.

### GET /api/v2/youtube/transcript — 1 credit

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/transcript\
?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=true" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param               | Required | Default | Validation                      |
| ------------------- | -------- | ------- | ------------------------------- |
| `video_url`         | yes      | —       | YouTube URL or 11-char video ID |
| `format`            | no       | `json`  | `json` or `text`                |
| `include_timestamp` | no       | `true`  | `true` or `false`               |
| `send_metadata`     | no       | `false` | `true` or `false`               |

Accepts: `https://youtube.com/watch?v=ID`, `https://youtu.be/ID`, `youtube.com/shorts/ID`, or bare `ID`.

**Response** (`format=json`):

```json
{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": [
    { "text": "We're no strangers...", "start": 18.0, "duration": 3.5 }
  ],
  "metadata": { "title": "...", "author_name": "...", "author_url": "..." }
}
```

### GET /api/v2/youtube/search — 1 credit

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=20" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param   | Required | Default | Validation            |
| ------- | -------- | ------- | --------------------- |
| `q`     | yes      | —       | 1-200 chars (trimmed) |
| `type`  | no       | `video` | `video` or `channel`  |
| `limit` | no       | `20`    | 1-50                  |

**Response** (`type=video`):

```json
{
  "results": [
    {
      "type": "video",
      "videoId": "dQw4w9WgXcQ",
      "title": "Rick Astley - Never Gonna Give You Up",
      "channelId": "UCuAXFkgsw1L7xaCfnd5JJOw",
      "channelTitle": "Rick Astley",
      "channelHandle": "@RickAstley",
      "channelVerified": true,
      "lengthText": "3:33",
      "viewCountText": "1.5B views",
      "publishedTimeText": "14 years ago",
      "hasCaptions": true,
      "thumbnails": [{ "url": "...", "width": 120, "height": 90 }]
    }
  ],
  "result_count": 20
}
```

**Response** (`type=channel`):

```json
{
  "results": [
    {
      "type": "channel",
      "channelId": "UCuAXFkgsw1L7xaCfnd5JJOw",
      "title": "Rick Astley",
      "handle": "@RickAstley",
      "subscriberCount": "4.2M subscribers",
      "verified": true,
      "rssUrl": "https://www.youtube.com/feeds/videos.xml?channel_id=UC..."
    }
  ],
  "result_count": 5
}
```

### GET /api/v2/youtube/channel/resolve — FREE (0 credits)

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TED" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param   | Required | Validation                              |
| ------- | -------- | --------------------------------------- |
| `input` | yes      | 1-200 chars — @handle, URL, or UC... ID |

**Response:**

```json
{ "channel_id": "UCsT0YIqwnpJCM-mx7-gSA4Q", "resolved_from": "@TED" }
```

If input is already a valid `UC[a-zA-Z0-9_-]{22}` ID, returns immediately without lookup.

### GET /api/v2/youtube/channel/videos — 1 credit/page

```bash
# First page (100 videos)
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"

# Most-viewed first (channel Videos tab, ~30 videos)
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA&sort=popular" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"

# Next pages (repeat the same sort)
curl -s "https://transcriptapi.com/api/v2/youtube/channel/videos?continuation=TOKEN&sort=popular" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param          | Required    | Validation                                    |
| -------------- | ----------- | --------------------------------------------- |
| `channel`      | conditional | `@handle`, channel URL, or `UC...` ID         |
| `tab`          | no          | `videos` (default), `shorts`, or `streams`    |
| `sort`         | no          | `latest`, `popular`, or `oldest` (omit for the uploads feed) |
| `continuation` | conditional | non-empty string (next pages)                 |

Provide exactly one of `channel` or `continuation`.

**Sorting.** Add sort=latest, popular, or oldest to channel/videos to get a channel's videos in the order you want, for example its most-popular uploads first. A sorted page returns about 30 videos (an unsorted page returns about 100), and every page costs the same 1 credit.

When paging, send the same sort on each request.

Every item carries `members_only`, `true` only when YouTube badges it "Members only", and those items have no `viewCountText`. Items from `tab=streams` carry `lengthText` and `publishedTimeText` (for example `Streamed 2 years ago`); `tab=shorts` returns `null` for both, because YouTube's Shorts grid publishes neither. On the channel-tab feeds (`tab=videos` with `sort`, `tab=shorts`, `tab=streams`) `channelId`, `channelTitle`, `channelHandle` and `index` are `null`.

**Response:**

```json
{
  "results": [{
    "videoId": "abc123xyz00",
    "title": "Latest Video",
    "channelId": "UCsT0YIqwnpJCM-mx7-gSA4Q",
    "channelTitle": "TED",
    "channelHandle": "@TED",
    "lengthText": "15:22",
    "viewCountText": "3.2M views",
    "publishedTimeText": "2 years ago",
    "thumbnails": [...],
    "index": "0",
    "members_only": false
  }],
  "playlist_info": {"title": "Uploads from TED", "numVideos": "5000"},
  "continuation_token": "4qmFsgKlARIYVVV1...",
  "has_more": true
}
```

### GET /api/v2/youtube/channel/latest — FREE (0 credits)

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TED" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param     | Required | Validation                                |
| --------- | -------- | ----------------------------------------- |
| `channel` | yes      | `@handle`, channel URL, or `UC...` ID     |

Returns last 15 videos via RSS with exact view counts and ISO timestamps.

**Response:**

```json
{
  "channel": {
    "channelId": "...",
    "title": "TED",
    "author": "TED",
    "url": "..."
  },
  "results": [
    {
      "videoId": "abc123xyz00",
      "title": "Latest Video",
      "published": "2026-01-30T16:00:00Z",
      "viewCount": "2287630",
      "description": "Full description...",
      "thumbnail": { "url": "...", "width": "480", "height": "360" }
    }
  ],
  "result_count": 15
}
```

### GET /api/v2/youtube/channel/search — 1 credit

```bash
curl -s "https://transcriptapi.com/api/v2/youtube/channel/search\
?channel=@TED&q=climate+change&limit=30" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param     | Required | Validation                                |
| --------- | -------- | ----------------------------------------- |
| `channel` | yes      | `@handle`, channel URL, or `UC...` ID     |
| `q`       | yes      | 1-200 chars                               |
| `limit`   | no       | 1-50 (default 30)                         |

### GET /api/v2/youtube/playlist/videos — 1 credit/page

```bash
# First page
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist=PL_PLAYLIST_ID" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"

# Next pages
curl -s "https://transcriptapi.com/api/v2/youtube/playlist/videos?continuation=TOKEN" \
  -H "Authorization: Bearer $TRANSCRIPT_API_KEY" \
  -H "User-Agent: YourAgent/1.0"
```

| Param          | Required    | Validation                                           |
| -------------- | ----------- | ---------------------------------------------------- |
| `playlist`     | conditional | Playlist URL or ID (`PL`/`UU`/`LL`/`FL`/`OL` prefix) |
| `continuation` | conditional | non-empty string                                     |

## Credit Costs

| Endpoint        | Cost     |
| --------------- | -------- |
| transcript      | 1        |
| search          | 1        |
| channel/resolve | **free** |
| channel/search  | 1        |
| channel/videos  | 1/page   |
| channel/latest  | **free** |
| playlist/videos | 1/page   |

## Errors

| Code     | Meaning           | Action                                              |
| -------- | ----------------- | --------------------------------------------------- |
| 401      | Bad API key       | Check key, re-run setup                             |
| 402      | No credits        | Top up at transcriptapi.com/billing                 |
| 403/1010 | Cloudflare block  | Add or fix User-Agent header                        |
| 404      | Not found         | Video/channel/playlist doesn't exist or no captions |
| 408      | Timeout/retryable | Retry once after 2s                                 |
| 422      | Validation error  | Check param format                                  |
| 429      | Rate limited      | Wait, respect Retry-After                           |

## Tips

- When user shares YouTube URL with no instruction, fetch transcript and summarize key points.
- Use `channel/latest` (free) to check for new uploads before fetching transcripts — pass @handle directly.
- For research: search → pick videos → fetch transcripts.
- Free tier: 100 credits, 300 req/min. Starter ($5/mo): 1,000 credits, 300 req/min.

「内容创作」分类下的热门技能

李白.Skill内容创作

李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹,将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写(词汇→句式→内容→逻辑→语气)和六步质控流水线,确保最终文本通过人工审查。

↓ 125.0万★ 121user_741dc82b
libai-skill内容创作

李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹,将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写和质控流水线,确保最终文本通过人工审查。

↓ 101.8万★ 11user_814dbe54
文章去AI味工具内容创作

识别并去掉文本里的 AI 写作痕迹,让文字读起来更像人写。

↓ 95.1万★ 767user_ab5ae6ee
视频号爆款短视频拆解(付费版:全能)【零一数科·出品】内容创作

【零一数科·出品】视频号爆款短视频拆解(全能版)(付费版)。视频号爆款短视频拆解(付费版:全能)。一键拆解爆款,把一条视频号视频拆成结构分段、爆款归因、六维评分和可借鉴策略,照着学照着抄。支持视频号分享链接和本地视频,付费全能版远端分析,1–5 分钟出可视化 HTML 报告。

↓ 91.9万★ 116u_c19e970c
视频号挂车爆单短视频脚本生成【零一数科·出品】内容创作

【零一数科·出品】视频号挂车爆单短视频脚本生成(付费版)。一条链接二创脚本,丢进爆款视频号链接即以此骨架改写成你的挂车脚本,或按方向/目的/商品原创多条口播脚本(含分段表、口播全文、六维质检评分)。

↓ 55.4万★ 39u_c19e970c
Humanizer内容创作

把文本里 AI 写作的典型痕迹挑出来并改写得更自然,同时保留原意的写作编辑技能。

↓ 50.9万★ 1,116B*T
中文公文写作内容创作

用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。

↓ 41.3万★ 84gongyu0918
视频号爆款文案生成(体验版)【零一数科·出品】内容创作

【零一数科·出品】视频号爆款文案生成(体验版)。免费免登录出脚本,给创作目的、行业、受众、选题就按爆款结构(Hook-中段-CTA、节奏标签)产出口播脚本,信息不全也能按爆款潜质兜底。本地运行、无需 Key,零成本上手。

↓ 33.9万★ 94u_c19e970c

Rohit Das 的其他技能

数据月份:2026-10 · 下载/星标数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。