One Video, Five Outputs: Repurpose YouTube Into Articles, Threads, and Shorts Scripts

Description and use

An automation workflow turns a single YouTube video into five publishable outputs—article, thread, shorts scripts—by fetching transcript with timestamps via Apify and generating content with GPT‑4o‑mini.

Problem

Automating the conversion of a single YouTube video into multiple publishable formats requires a reliable transcript with timestamps and a structured pipeline to generate content, which is often missing from simple caption scrapers.

Outcome

The pipeline produces five publishable outputs from one video with minimal manual effort, ensuring consistency and verifiability via timestamps.

Workflow

• 1. Call Apify actor to fetch transcript, segments, and SRT for a YouTube URL.
• 2. Store the returned text, segments, and SRT for reuse across outputs.
• 3. Generate an 800‑word article with verbatim quotes and timestamp markers using GPT‑4o‑mini.
• 4. Score segments for standalone punch, select top 7, and produce a 7‑post thread with timestamps.
• 5. Identify hook and beats from segments to script 30‑60 second shorts, including cut points and timestamps.

Evidence

The trick is structural, not clever prompting. Hand the LLM the full text plus an outline, and require verbatim quotes so the draft stays grounded instead of drifting into generic summary.

Source

Threads want one idea per post and a hook that earns the click. Score segments for "standalone punch" with a dead simple heuristic, then expand the winners.

Source