nextcloud / nextcloud/integration_openai

Audio transcription: allow user to select model

Open
#338 4 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
PHP
Stars
75
Forks
32
Avg merge
9d 8h
Merged PRs (30d)
4

Description

Describe the feature you'd like to request

When transcribing an audio file the user is not offered the option to select the model, when showing advanced options (3-dots menu). Only the input language can be changed.

Image
Describe the solution you'd like

It would be useful to give the user the options to select all the models able to process transcription and available in the backend.

Other AI tasks do already have this option (text processing, translation, even text-to-speech that is kind of a mirror capability to transcription).

I'm using Nextcloud Assistant 2.12.0 on Nextcloud 32.0.5 with LocalAI 3.10.1 as backend.

Describe alternatives you've considered

The administrator can change the model in the Assistant settings, but that applies to all the users.

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

Start by tracing the audio transcription advanced-options UI and compare it with model selection for text processing, translation, and text-to-speech. Check how the backend exposes models available for transcription. Done means users can choose an available transcription model without changing the administrator's default for everyone.

Written by the indexing model from the issue text.

Assessment

Tech stack
php
Domain
backend, frontend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.