Output format transformations #7

Closed
opened 2026-09-01 20:38:54 +00:00 by Mark · 1 comment
Owner

JSON works. Need human-readable formats that match media:youtube-content:

  • Chapters: group segments by topic shift, output timestamped chapter list
  • Summary: 5-10 sentence overview
  • Chapter summaries: chapters + per-chapter paragraph summary
  • Thread: Twitter/X format — numbered posts, each <280 chars
  • Blog post: title, sections, takeaways
  • Quotes: notable quotes with timestamps

Where: pure Python post-processing module that takes the JSON output + the format flag. No model calls, just text ops. Cheap to run after ASR completes.

CLI: --format chapters|summary|thread|blog|quotes|json (default: json)

JSON works. Need human-readable formats that match `media:youtube-content`: - **Chapters**: group segments by topic shift, output timestamped chapter list - **Summary**: 5-10 sentence overview - **Chapter summaries**: chapters + per-chapter paragraph summary - **Thread**: Twitter/X format — numbered posts, each <280 chars - **Blog post**: title, sections, takeaways - **Quotes**: notable quotes with timestamps **Where:** pure Python post-processing module that takes the JSON output + the format flag. No model calls, just text ops. Cheap to run after ASR completes. **CLI:** `--format chapters|summary|thread|blog|quotes|json` (default: json)
Author
Owner

Fixed in commit. Closing.

Fixed in commit. Closing.
Mark closed this issue 2026-09-06 00:35:25 +00:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
Mark/whisper-transcribe#7
No description provided.