nextcloud / nextcloud/integration_openai
Allow transcription and summary of big nextcloud talk recordings
Nobody has claimed this yet.
- Dominant language
- PHP
- Stars
- 75
- Forks
- 32
- Avg merge
- 9d 8h
- Merged PRs (30d)
- 4
Description
Describe the feature you'd like to request
Open AI have limit of 25MB file upload
https://community.openai.com/t/whisper-api-increase-file-limit-25-mb/566754
Do not upload video webm file.
Encode it as light ogg file and upload a smaller file.
Describe the solution you'd like
https://github.com/nextcloud/integration_openai/pull/204
Describe alternatives you've considered
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the referenced pull request #204 and tracing the existing Nextcloud Talk recording transcription and summary upload flow. Verify how WebM recordings are handled and what the OpenAI upload path expects; done means large recordings are converted to a smaller OGG upload that stays within the 25 MB limit and still supports transcription and summaries.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- php
- Domain
- audio-video-rtc, backend
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100