nextcloud / nextcloud/spreed

Propose relevant information during Talk calls from notes/files

Open
#17,676 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement feature: AI ✨ feature: call 📹 feature: integration 📦
Dominant language
JavaScript
Stars
2.2k
Forks
586
Avg merge
18h 27m
Merged PRs (30d)
333

Description

[!TIP]

How to use GitHub
  • Please use the 👍 reaction to show that you are affected by the same issue.
  • Please don't comment if you have no relevant information to add. It's just extra noise for everyone subscribed to this issue.
  • Subscribe to receive notifications on status change and new comments.

Feature request

Which Nextcloud Version are you currently using: 33
Is your feature request related to a problem? Please describe.
When having calls, finding the right information can be challenging. Also it might be useful to get reminded of things discussed previously and written down in protocols.

Describe the solution you'd like
With activated transcription of calls, context searches could be performed in the background for certain events, e.g. if the AI recognizes questions or points where it comes to decisions. Then, relevant information could be proposed in the UI.

Describe alternatives you've considered
Performing the searches manually or upfront.

Additional context
There is a Mac tool doing something similar: https://github.com/yazinsai/OpenOats

Might belong more to the Assistant, I'm happy to move that where ever it makes sense.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files or tests. Start by reviewing the existing Talk transcription and Assistant-related entry points, then clarify which events, information sources, and UI should be supported. Done requires an agreed implementation scope and acceptance criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
javascript
Domain
ai, audio-video-rtc
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.