Youtube Full

ZeroPointRepo/youtube-skills/skills/youtube-full

作者 ZeroPointRepo4f7994b94e7d5e250c3b51102d609992e04d5d0d無授權條款1K 個星標收錄於 2026年10月9日更新於 2026年10月9日儲存庫2 天前更新

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, first looks, 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.

AI 產生的概覽

透過 TranscriptAPI 服務取得 YouTube 字幕、影片中繼資料、搜尋結果,以及頻道與播放清單資料。

功能
這個技能記錄了呼叫 TranscriptAPI.com 取得 YouTube 資料的 HTTP 請求:影片字幕(可選時間戳與中繼資料)、影片中繼資料、關鍵字搜尋、頻道解析、頻道內容串、頻道內搜尋、頻道簡介、播放清單、社群貼文與精選區塊。它以 API 回應形式傳回字幕、中繼資料與清單資料,並包含 API 金鑰的設定說明與可直接執行的請求範例。這個技能只提供說明,不附帶指令碼。
適用情境
當任務涉及 YouTube 影片、頻道或播放清單時使用,例如摘要影片、引用或翻譯口述內容、透過演講或教學研究某個主題,或追蹤頻道更新。不適用於上傳影片或管理帳號。
執行需求
需要連線至 transcriptapi.com 的網路存取,以及 TRANSCRIPT_API_KEY 環境變數(免費帳號提供 100 點數)。請求需要 Authorization bearer 標頭與 User-Agent 標頭。不需要其他執行環境或相依套件,也不包含指令碼。

YouTube Full

Complete YouTube toolkit via TranscriptAPI.com. Everything in one skill.

Setup

If $TRANSCRIPT_API_KEY is not set, read references/auth-setup.md [blocked] 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 — consult this for the latest parameters and schemas.

Transcript — 1 credit

http
GET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=trueAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
ParamRequiredDefaultValues
video_urlyes—YouTube URL or 11-char video ID
formatnojsonjson, text
include_timestampnotruetrue, false
send_metadatanofalsetrue, false

Response (format=json):

json
{  "video_id": "dQw4w9WgXcQ",  "language": "en",  "transcript": [{ "text": "...", "start": 18.0, "duration": 3.5 }],  "metadata": { "title": "...", "author_name": "...", "author_url": "..." }}

Video Info & Metadata

http
# Free — languages available for the transcript endpointGET https://transcriptapi.com/api/v2/youtube/info?video_url=VIDEO_URLAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# 1 credit — rich metadata (views, likes, description, duration, tags)GET https://transcriptapi.com/api/v2/youtube/video/metadata?video_url=VIDEO_URL&include=details,relatedAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

include on video/metadata accepts details and/or related. Naming: /video/metadata was previously /video/info — the old path still works but is deprecated.

Search — 1 credit/page

http
# VideosGET https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=video&limit=20Authorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# Channels, playlists, or moviesGET https://transcriptapi.com/api/v2/youtube/search?q=QUERY&type=channel&limit=10Authorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
ParamRequiredDefaultValidation
qyes—1-200 chars
typenovideovideo, channel, playlist, movie
sortnorelevancerelevance, views (first page only)
upload_dateno—hour, today, week, month, year (videos, first page)
durationno—short, medium, long (videos, first page)
featuresno—e.g. hd,subtitles,cc (first page)
limitno201-50

Channels

All channel endpoints accept channel — an @handle, channel URL, or UC... channel ID. No need to resolve first.

Resolve handle — FREE

http
GET https://transcriptapi.com/api/v2/youtube/channel/resolve?input=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Response: {"channel_id": "UC...", "resolved_from": "@TED"}

Latest 15 videos — FREE

http
GET https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Returns exact viewCount and ISO published timestamps.

Channel feed (videos/shorts/streams) — 1 credit/page

http
# First page (100 items, tab defaults to "videos")GET https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA&tab=videosAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# Most-viewed first (channel Videos tab, ~30 items)GET https://transcriptapi.com/api/v2/youtube/channel/videos?channel=@NASA&sort=popularAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# Next pages (repeat the same tab AND sort)GET https://transcriptapi.com/api/v2/youtube/channel/videos?continuation=TOKEN&sort=popularAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Provide exactly one of channel or continuation. tab is videos (default), shorts, or streams. Response includes continuation_token and has_more.

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.

Item fields. Every item carries members_only, true only when YouTube badges it "Members only", and those items have no viewCountText. tab=streams items 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.

Search within channel — 1 credit

http
GET https://transcriptapi.com/api/v2/youtube/channel/search?channel=@TED&q=QUERY&limit=30Authorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Channel profile — 1 credit

http
GET https://transcriptapi.com/api/v2/youtube/channel/info?channel=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Returns title, handle, verified flag, subscriber/video counts, description, tags, thumbnails, banners, and availableTabs.

Channel playlists — 1 credit/page

http
GET https://transcriptapi.com/api/v2/youtube/channel/playlists?channel=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Returns each playlist's playlistId, title, url, videoCountText — feed a playlistId into the Playlists endpoint below.

Channel community posts — 1 credit/page

http
GET https://transcriptapi.com/api/v2/youtube/channel/posts?channel=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Channel curated sections — 1 credit

http
GET https://transcriptapi.com/api/v2/youtube/channel/sections?channel=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

tab is featured (default, Home page), podcasts, or releases.

Playlists — 1 credit/page

Accepts playlist — a YouTube playlist URL or playlist ID.

http
# First pageGET https://transcriptapi.com/api/v2/youtube/playlist/videos?playlist=PL_IDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# Next pagesGET https://transcriptapi.com/api/v2/youtube/playlist/videos?continuation=TOKENAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Valid ID prefixes: PL, UU, LL, FL, OL. Response includes playlist_info, results, continuation_token, has_more.

Credit Costs

EndpointCost
transcript1
infofree
video/metadata1
search1/page
channel/resolvefree
channel/info1
channel/latestfree
channel/videos1/page
channel/search1
channel/playlists1/page
channel/posts1/page
channel/sections1
playlist/videos1/page

Validation Rules

FieldRule
channel@handle, channel URL, or UC... ID
playlistPlaylist URL or ID (PL/UU/LL/FL/OL prefix)
q1-200 chars
type (search)video (default), channel, playlist, movie
tab (channel/videos)videos (default), shorts, streams
sort (channel/videos)latest, popular, oldest (omit for the uploads feed)
tab (channel/sections)featured (default), podcasts, releases
include (video/metadata)details, related (comma-separated)
limit1-50

Errors

CodeMeaningAction
401Bad API keyCheck key
402No creditstranscriptapi.com/billing
403/1010Cloudflare blockAdd or fix User-Agent header
404Not foundResource doesn't exist or no captions
408TimeoutRetry once after 2s
422Validation errorCheck param format
429Rate limitedWait, respect Retry-After

Typical Workflows

Research workflow: search → pick videos → fetch transcripts

http
# 1. SearchGET https://transcriptapi.com/api/v2/youtube/search?q=machine+learning+explained&limit=5Authorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# 2. TranscriptGET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_ID&format=text&include_timestamp=true&send_metadata=trueAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Channel monitoring: latest (free) → transcript

http
# 1. Latest uploads (free — pass @handle directly)GET https://transcriptapi.com/api/v2/youtube/channel/latest?channel=@TEDAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0
# 2. Transcript of latestGET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_ID&format=text&include_timestamp=true&send_metadata=trueAuthorization: Bearer $TRANSCRIPT_API_KEYUser-Agent: YourAgent/1.0

Free tier: 100 credits, 300 req/min. Starter ($5/mo): 1,000 credits.

Copy-paste examples

Every request in this file as a ready-to-run one-liner: references/curl-examples.md [blocked]

來源與署名

來源:ZeroPointRepo/youtube-skills位於skills/youtube-full提交4f7994b

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架