Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4974] [FEAT]: Consistency between transcription settings and audio ingestion paths #3122

New Issue
Closed
opened 2026-02-22 18:32:42 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:32:42 -05:00
Owner
Copy Link
Copy Source

Originally created by @danmcrae1 on GitHub (Feb 7, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4974

What would you like to see?

Description
I’m seeing an inconsistency between transcription settings and where audio transcription is actually available.

Observed behavior

In Settings → Transcription Model Preference, I can select AnythingLLM Built-In → Xenova/whisper-large.

Workspaces do not accept audio files (tested .wav and .mp3), so I can’t use the selected transcription model there.

The Meeting Assistant does accept audio files, but appears to use a fixed transcription engine (UI labels it “Parakeet”) and does not respect the Transcription Model Preference.

Expected behavior

Either Workspaces should accept audio and use the configured transcription preference, or

Meeting Assistant should respect the Transcription Model Preference (or provide its own model/provider selector).

Steps to reproduce

Set Transcription Provider = AnythingLLM Built-In; Model = Xenova/whisper-large.

Attempt to upload .wav or .mp3 into a Workspace → not accepted.

Upload the same file into Meeting Assistant → accepted, but transcription provider/model cannot be changed.

Notes

Searching the repo for parakeet returns no matches, so the Meeting Assistant transcription provider may be referenced internally under a different name or implemented outside the main repo.

Screenshot

Image

attached.

Originally created by @danmcrae1 on GitHub (Feb 7, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4974 ### What would you like to see? Description I’m seeing an inconsistency between transcription settings and where audio transcription is actually available. Observed behavior In Settings → Transcription Model Preference, I can select AnythingLLM Built-In → Xenova/whisper-large. Workspaces do not accept audio files (tested .wav and .mp3), so I can’t use the selected transcription model there. The Meeting Assistant does accept audio files, but appears to use a fixed transcription engine (UI labels it “Parakeet”) and does not respect the Transcription Model Preference. Expected behavior Either Workspaces should accept audio and use the configured transcription preference, or Meeting Assistant should respect the Transcription Model Preference (or provide its own model/provider selector). Steps to reproduce Set Transcription Provider = AnythingLLM Built-In; Model = Xenova/whisper-large. Attempt to upload .wav or .mp3 into a Workspace → not accepted. Upload the same file into Meeting Assistant → accepted, but transcription provider/model cannot be changed. Notes Searching the repo for parakeet returns no matches, so the Meeting Assistant transcription provider may be referenced internally under a different name or implemented outside the main repo. Screenshot <img width="1074" height="439" alt="Image" src="https://github.com/user-attachments/assets/c508daf6-725d-46b8-b11e-29081eff5fe4" /> attached.
yindo added the enhancementfeature request labels 2026-02-22 18:32:42 -05:00
yindo closed this issue 2026-02-22 18:32:42 -05:00
yindo commented 2026-02-22 18:32:43 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 9, 2026):

Correct, it is confusing and we are going to patch this issue out in desktop. TLDR; the transcription provider using ONNXruntime whisper is totally busted right now.

We are going to remove the transcription choice because it is broken on desktop and rely on the transcription engine, which is much more accurate and performant to do all transcriptions, audio handling, and more.

@timothycarambat commented on GitHub (Feb 9, 2026): Correct, it is confusing and we are going to patch this issue out in desktop. TLDR; the transcription provider using ONNXruntime whisper is totally busted right now. We are going to remove the transcription choice because it is broken on desktop and rely on the transcription engine, which is much more accurate and performant to do all transcriptions, audio handling, and more.
yindo commented 2026-02-22 18:32:43 -05:00
Author
Owner
Copy Link
Copy Source

@danmcrae1 commented on GitHub (Feb 9, 2026):

Thank you.

@danmcrae1 commented on GitHub (Feb 9, 2026): Thank you.
yindo changed title from [FEAT]: Consistency between transcription settings and audio ingestion paths to [GH-ISSUE #4974] [FEAT]: Consistency between transcription settings and audio ingestion paths 2026-06-05 14:50:24 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#3122
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?