open-easthampton/ideas
1
0
Fork 0
Code Issues 8 Pull requests Projects Releases Packages Wiki Activity Actions

Create transcripts of city meetings #2

New issue
Open
opened 2026-08-02 16:36:50 -04:00 by mike · 0 comments
mike commented 2026-08-02 16:36:50 -04:00
Owner
Copy link

Automatically create something like this from YouTube videos:

https://openeasthampton.com/2025-10-13-mayoral-forum-transcript/

I have tooling for this, but it's pretty clunky and manual right now.

I'd like to make something that:

  • Can take a YouTube URL as input
  • Transcribes the video and does speaker diarization to identify changes in speakers
    • Bonus if it can store voice signatures so we don't have to manually identify recurring characters every video like the mayor and city council members
  • Redact people's home addresses from the transcript
    • During public speak, people have to state their address, but it's not useful to highlight that information
  • Auto-correct common AI errors that are Easthampton specific
    • e.g., always rewrite "East Hampton" to "Easthampton"
  • Integrate a manual corrections file that layers corrections on top of the auto-correct
  • Integrate manual identification of different speakers by name

Also nice if you can do full-text search across transcripts to find all mentions of a topic like "flock" or "license plate readers."

Automatically create something like this from YouTube videos: https://openeasthampton.com/2025-10-13-mayoral-forum-transcript/ I have tooling for this, but it's pretty clunky and manual right now. I'd like to make something that: - Can take a YouTube URL as input - Transcribes the video and does speaker diarization to identify changes in speakers - Bonus if it can store voice signatures so we don't have to manually identify recurring characters every video like the mayor and city council members - Redact people's home addresses from the transcript - During public speak, people have to state their address, but it's not useful to highlight that information - Auto-correct common AI errors that are Easthampton specific - e.g., always rewrite "East Hampton" to "Easthampton" - Integrate a manual corrections file that layers corrections on top of the auto-correct - Integrate manual identification of different speakers by name Also nice if you can do full-text search across transcripts to find all mentions of a topic like "flock" or "license plate readers."
mike added this to the Ideas project 2026-08-02 16:57:23 -04:00
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Ideas
Assignees
Clear assignees
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
open-easthampton/ideas#2
No description provided.