[GH-ISSUE #4838] [FEAT]: Allow the option to run a seperate local transcription model #3048

Closed
opened 2026-02-22 18:32:24 -05:00 by yindo · 0 comments
Owner

Originally created by @natemartin03 on GitHub (Jan 8, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4838

What would you like to see?

AnythingLLM has two options for a transcription model; AnythingLLM built-in (Whisper-small or Whisper-large) and OpenAI.

I already run a local whisper container that I use for other services, such as home assistant, and I have already set up to utilize my GPU. Having this second built-in Whisper model just adds bloat, and honestly decreases performance.
We should have the option to use a local url to locally host our own transcription models.

Originally created by @natemartin03 on GitHub (Jan 8, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4838 ### What would you like to see? AnythingLLM has two options for a transcription model; AnythingLLM built-in (Whisper-small or Whisper-large) and OpenAI. I already run a local whisper container that I use for other services, such as home assistant, and I have already set up to utilize my GPU. Having this second built-in Whisper model just adds bloat, and honestly decreases performance. We should have the option to use a local url to locally host our own transcription models.
yindo added the enhancementfeature request labels 2026-02-22 18:32:24 -05:00
yindo closed this issue 2026-02-22 18:32:24 -05:00
yindo changed title from [FEAT]: Allow the option to run a seperate local transcription model to [GH-ISSUE #4838] [FEAT]: Allow the option to run a seperate local transcription model 2026-06-05 14:50:00 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#3048