Apify Youtube Transcripts LLM Training Data

Build LLM training data from YouTube transcripts in bulk with the Apify Actor johnvc/YoutubeTranscripts. Feed it an array of video URLs and get one clean row per video, with non_timestamped transcript text ready for tokenization, timestamped snippets, language_code, and provenance metadata (title, channel_name, upload_date, view_count) for dataset documentation. Filter by language or translate every transcript into one target language for a consistent corpus. Use when the user wants LLM training data from videos, a fine-tuning or RAG corpus from YouTube, bulk YouTube transcripts for machine le

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add johnisanerd/claude-skill-youtube-transcripts-llm-training-data --skill apify-youtube-transcripts-llm-training-data
Manual install
git clone --depth 1 https://github.com/johnisanerd/claude-skill-youtube-transcripts-llm-training-data.git /tmp/claude-skill-youtube-transcripts-llm-training-data
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skill-youtube-transcripts-llm-training-data/apify-youtube-transcripts-llm-training-data ~/.claude/skills/apify-youtube-transcripts-llm-training-data

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# YouTube Transcripts as LLM Training Data

Turn a list of YouTube videos into a clean text corpus for LLM fine-tuning, RAG, or analysis. One run takes an array of URLs and returns one row per video: the full transcript as a single text field, plus the provenance metadata (title, channel, upload date, views) a documented dataset needs.

## When to use this skill

- The user wants LLM training data, a fine-tuning corpus, or RAG documents sourced from YouTube videos.
- They want bulk transcripts from a channel dump, a playlist export, or a keyword-collected URL list.
- They want spoken-video content as text without running their own speech-to-text.
- They need a single-language corpus from mixed-language sources (translate everything to one target).

Not for: discovering which videos to include (collect URLs first; see the chain table in `references/actor-index.md`), videos without caption tracks (those return error rows), or verbatim audio ground truth (captions are YouTube's own tracks, not fresh ASR).

## What you get (one row per video)
Read the full skill on GitHub

Details

Skill name
apify-youtube-transcripts-llm-training-data
Path
apify-youtube-transcripts-llm-training-data/SKILL.md
Repo updated
17 July 2026

FAQ

What does the Apify Youtube Transcripts LLM Training Data skill do?

Build LLM training data from YouTube transcripts in bulk with the Apify Actor johnvc/YoutubeTranscripts. Feed it an array of video URLs and get one clean row per video, with non_timestamped transcript text ready for tokenization, timestamped snippets, language_code, and provenance metadata (title, channel_name, upload_date, view_count) for dataset documentation. Filter by language or translate every transcript into one target language for a consistent corpus. Use when the user wants LLM training data from videos, a fine-tuning or RAG corpus from YouTube, bulk YouTube transcripts for machine le

How do I install the Apify Youtube Transcripts LLM Training Data skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add johnisanerd/claude-skill-youtube-transcripts-llm-training-data --skill apify-youtube-transcripts-llm-training-data. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Related skills

Comment to Dm Cta

commentkeyword/instagram-mcp-server

Plan the "Comment KEYWORD and I'll DM you the link" call to action of an Instagram Reel or post, then set up the automatic DM in CommentKeyword so every commenter actually gets it. Use when editing, scripting, captioning or publishing a short-form video whose CTA asks viewers to comment a word, or when the user asks to set up comment-to-DM, "comment X to get Y", or a keyword auto-DM on Instagram.

Images, Video & AudioIn 1 list

Apify Youtube Transcript API

johnisanerd/claude-skill-youtube-transcript-api

Get YouTube transcripts as structured JSON with a hosted YouTube transcript API (the Apify Actor johnvc/YoutubeTranscripts). Pass one video URL or a batch array and get back non_timestamped text, timestamped snippets, language metadata, and optional SRT, VTT, and plain text formats, plus video title, channel, and view count. Works with standard videos and Shorts, handles language preference and translation, and runs from cloud IPs without IpBlocked errors. Use when the user wants a youtube transcript api, needs to get or download a YouTube transcript or subtitles, asks to extract the transcrip

Images, Video & AudioIn 1 list

Kavel Image

hanshs474/kavel-image-skill

Generate an image from a prompt through Kavel's anonymous endpoint — no API key, no account, no card. Use when the user asks for an image, a poster, a thumbnail, or any visual asset and there is no image model wired up. Photo edits and video need a Kavel API key.

Images, Video & AudioIn 1 list

Cliptude Plan

cliptude/cliptude

Plan every visual of a Cliptude video yourself — the look (theme, colours, style, music), every motion graphic and its text and timing, the search query, person or URL behind every shot, the transition on every cut, two-image reveals and every sound effect — and have Cliptude only voice, source and render it. Use for Faceless Documentary, Faceless Top 10, Avatar Video and Vector Explainer templates when the user wants the agent to direct the video (create_plan_job / cliptude plan-job), or asks to review or edit the plan before production.

Images, Video & AudioIn 1 list

Make Faceless Video

airdropfi/autoshort-skills

Make a narrated, captioned faceless short video (AI images and AI voice) on the user's own AutoShort or StoryShort account. Works with either MCP server, detects which one is connected, agrees the script with the user, shows the credit price the server returns and renders only after an explicit yes, then polls the render and returns the video link. Use when the user wants to make, draft, render or publish a short video, YouTube Short, TikTok or Reel.

Images, Video & AudioIn 1 list

Swedish Mentor

1

mh-mansouri/help_with_swedish

Mentor Swedish language learners by selecting YouTube video clips and podcast episodes by CEFR level and skill (listening, reading, writing, speaking). Triggers on Swedish learning path, YouTube clips for Swedish, podcasts for Swedish, SFI videos, level assessment for svenska, or requests for Peter SFI / Lätt Svenska med Oskar / Radio Sweden på lätt svenska / Klartext recommendations.

Images, Video & AudioIn 1 list

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.