Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1603] [FEAT]: Add speech-to-text prompting possibility activated with a key combination #1041

New Issue
Closed
opened 2026-02-22 18:22:50 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:22:50 -05:00
Owner
Copy Link
Copy Source

Originally created by @Quanderr on GitHub (Jun 4, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1603

What would you like to see?

Adding the possibility of prompting the chat with speach would greatly improve the user experience because of the time optimisation.

The common use case for the AnythingLLM is to perform RAG on some documents/books/other source materials and then Q&A against them. The process usually involves research performed by the user while augmenting his processing capabilities by asking about some data/calculations the LLM.

Currently the flow looks like this:

Research document -> question arises -> switch window and your mind focus to the AnythingLLM -> think about precise way of specifying the prompt -> Write the prompt and wait for the answer.

It doesn't seem like a big trouble, but considering that:

1 - you are doing it very often
2 - it causes you to lose focus on the thing/though that you had before (what is the big distraction as it takes time to re-focus again)

It can and will grow into a significant amount of time.

What I'd love to see is the following:

Research document -> press key combination -> ask the question verbally -> continue to research document without losing focus & eye contact -> eventually see the LLM answer afterwards

Originally created by @Quanderr on GitHub (Jun 4, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1603 ### What would you like to see? Adding the possibility of prompting the chat with speach would greatly improve the user experience because of the time optimisation. The common use case for the AnythingLLM is to perform RAG on some documents/books/other source materials and then Q&A against them. The process usually involves research performed by the user while augmenting his processing capabilities by asking about some data/calculations the LLM. Currently the flow looks like this: Research document -> question arises -> switch window and your mind focus to the AnythingLLM -> think about precise way of specifying the prompt -> Write the prompt and wait for the answer. It doesn't seem like a big trouble, but considering that: 1 - you are doing it very often 2 - it causes you to lose focus on the thing/though that you had before (what is the big distraction as it takes time to re-focus again) It can and will grow into a significant amount of time. What I'd love to see is the following: Research document -> press key combination -> ask the question verbally -> continue to research document without losing focus & eye contact -> eventually see the LLM answer afterwards
yindo added the enhancementfeature request labels 2026-02-22 18:22:50 -05:00
yindo closed this issue 2026-02-22 18:22:51 -05:00
yindo changed title from [FEAT]: Add speech-to-text prompting possibility activated with a key combination to [GH-ISSUE #1603] [FEAT]: Add speech-to-text prompting possibility activated with a key combination 2026-06-05 14:38:39 -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#1041
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?