mirror of
https://github.com/open-webui/open-webui.git
synced 2026-05-06 19:08:59 -05:00
[GH-ISSUE #2450] feature - voice chat support: ask a question quickly with voice and listen to the response without having to break away from there current task. #12888
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#12888
Reference in New Issue
Block a user
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?
Originally created by @shakirahmad on GitHub (May 21, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/2450
Is your feature request related to a problem? Please describe.
It would be awesome to chat to LLM models with voice together with RAG and the new memory feature this could provide quick responses to questions a user might have. They can ask a question quickly with their voice and listen to the response without having to break away from there current task.
Describe the solution you'd like
I've found a solution which supports offline voice assistant using Ollama and Whisper speech recognition models completly offline.
The voice sounds very natural especially with premium voice support on mac and the response time is quick
https://github.com/apeatling/ollama-voice-mac
Feature request:
In addition it would useful to be able to interrupt mid response and ask another question
Example Scenario
Suppose I work for a company, I can upload all the clients info to a local private instance
I begin drafting an email I can quickly ask the via voice:
Regarding client x what plan are they on? when did they join our company? whats there membership
whilst i'm drafting the email etc