[GH-ISSUE #3927] [BUG]: use the STT (Speech-to-Text) of Gemini multimodal models directly #2501

Closed
opened 2026-02-22 18:29:57 -05:00 by yindo · 2 comments
Owner

Originally created by @yahyasamet on GitHub (May 31, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3927

How are you running AnythingLLM?

Docker (local)

What happened?

Gemini’s multimodal models do support audio input internally but only the local model is integrated .

Are there known steps to reproduce?

No response

Originally created by @yahyasamet on GitHub (May 31, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3927 ### How are you running AnythingLLM? Docker (local) ### What happened? Gemini’s multimodal models do support audio input internally but only the local model is integrated . ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:29:57 -05:00
yindo closed this issue 2026-02-22 18:29:57 -05:00
Author
Owner

@learning4life commented on GitHub (Jun 1, 2025):

Likely relate to:
https://github.com/Mintplex-Labs/anything-llm/issues/3885

@learning4life commented on GitHub (Jun 1, 2025): Likely relate to: https://github.com/Mintplex-Labs/anything-llm/issues/3885
Author
Owner

@timothycarambat commented on GitHub (Jun 3, 2025):

Correct, moving to #3885

@timothycarambat commented on GitHub (Jun 3, 2025): Correct, moving to #3885
yindo changed title from [BUG]: use the STT (Speech-to-Text) of Gemini multimodal models directly to [GH-ISSUE #3927] [BUG]: use the STT (Speech-to-Text) of Gemini multimodal models directly 2026-06-05 14:46:55 -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#2501