nextcloud / nextcloud/assistant
Audio transcription: allow video files to be transcribed
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 88
- Forks
- 43
- Avg merge
- 18h 49m
- Merged PRs (30d)
- 3
Description
Describe the feature you'd like to request
I'd like to be able to transcribe videos. Not sure about the formats but I'd start with .webm that are the formats that the Nextcloud Recording Server uses by default.
If I'm not wrong the Recording Server already sends .webm for transcription and LocalAI is able to manage it. Does this mean that it is just a matter of enabling this in the UI of the Assistant audio transcription panel? Not sure about it.
Describe the solution you'd like
To have the file picker allowing one to pick video files when starting a transcription.
Describe alternatives you've considered
Download the video file, transform it locally (I'm using this command FILE=file.webm; ffmpeg -i "${FILE}" -vn -ab 128k -ar 44100 -y "${FILE%.webm}.mp3";) then upload it back.
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 at the Assistant audio transcription panel and trace its file picker and upload flow. Check how .webm files from Nextcloud Recording Server are handled by LocalAI before deciding the supported formats; done means supported video files can be selected and transcribed without manual conversion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- javascript
- Domain
- audio-video-rtc, frontend
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100