I have searched the existing issues and discussions.
Problem Description
When using voice input, the system continuously listens and responds. However, it is overly sensitive—any movement, breath, or minor noise, such as a sneeze, causes it to stop responding. This creates a highly frustrating and nearly unusable experience, especially in everyday environments like a café or while doing house chores. While technically functional, the usability is severely compromised.
Desired Solution you'd like
Option 1: Mute Button – Add a “Mute” button, allowing users to toggle between listening and speaking. The user can click “Mute” to listen, then click again to speak, simulating a walkie-talkie functionality. While not the ideal solution, it would be a usable workaround.
Option 2: Adjust Sensitivity – Allow users to control the sensitivity of the voice input system. Users should be able to define the threshold for noise detection, so it doesn’t stop responding due to minor background noise.
Option 3: Delayed Response to Noise – Introduce a slight delay in detecting noise, where the system would not stop at the first noise but instead wait for a second one. This would reduce false triggers.
Alternatives Considered
Mute Button: This is a simple and quick fix, but it doesn’t align well with the seamless voice interaction experience. It is a last resort if the other solutions are not feasible.
No Sensitivity Control: There is no option for users to adjust sensitivity, which limits accessibility and practicality for different environments and use cases.
Additional Context
The primary issue is that the voice input system defeats its own purpose. It’s meant to free up the user’s hands for multitasking (e.g., while exercising, cooking, or cleaning), but excessive sensitivity forces the user to remain completely still to avoid interruptions. This compromises the core utility of voice commands. It would be ideal if the system could be fine-tuned to better handle normal noise in everyday environments while still providing accurate responses.
Originally created by @nonlinear on GitHub (May 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14500
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
When using voice input, the system continuously listens and responds. However, it is overly sensitive—any movement, breath, or minor noise, such as a sneeze, causes it to stop responding. This creates a highly frustrating and nearly unusable experience, especially in everyday environments like a café or while doing house chores. While technically functional, the usability is severely compromised.
### Desired Solution you'd like
Option 1: Mute Button – Add a “Mute” button, allowing users to toggle between listening and speaking. The user can click “Mute” to listen, then click again to speak, simulating a walkie-talkie functionality. While not the ideal solution, it would be a usable workaround.
Option 2: Adjust Sensitivity – Allow users to control the sensitivity of the voice input system. Users should be able to define the threshold for noise detection, so it doesn’t stop responding due to minor background noise.
Option 3: Delayed Response to Noise – Introduce a slight delay in detecting noise, where the system would not stop at the first noise but instead wait for a second one. This would reduce false triggers.
### Alternatives Considered
Mute Button: This is a simple and quick fix, but it doesn’t align well with the seamless voice interaction experience. It is a last resort if the other solutions are not feasible.
No Sensitivity Control: There is no option for users to adjust sensitivity, which limits accessibility and practicality for different environments and use cases.
### Additional Context
The primary issue is that the voice input system defeats its own purpose. It’s meant to free up the user’s hands for multitasking (e.g., while exercising, cooking, or cleaning), but excessive sensitivity forces the user to remain completely still to avoid interruptions. This compromises the core utility of voice commands. It would be ideal if the system could be fine-tuned to better handle normal noise in everyday environments while still providing accurate responses.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @nonlinear on GitHub (May 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14500
Check Existing Issues
Problem Description
When using voice input, the system continuously listens and responds. However, it is overly sensitive—any movement, breath, or minor noise, such as a sneeze, causes it to stop responding. This creates a highly frustrating and nearly unusable experience, especially in everyday environments like a café or while doing house chores. While technically functional, the usability is severely compromised.
Desired Solution you'd like
Option 1: Mute Button – Add a “Mute” button, allowing users to toggle between listening and speaking. The user can click “Mute” to listen, then click again to speak, simulating a walkie-talkie functionality. While not the ideal solution, it would be a usable workaround.
Option 2: Adjust Sensitivity – Allow users to control the sensitivity of the voice input system. Users should be able to define the threshold for noise detection, so it doesn’t stop responding due to minor background noise.
Option 3: Delayed Response to Noise – Introduce a slight delay in detecting noise, where the system would not stop at the first noise but instead wait for a second one. This would reduce false triggers.
Alternatives Considered
Mute Button: This is a simple and quick fix, but it doesn’t align well with the seamless voice interaction experience. It is a last resort if the other solutions are not feasible.
No Sensitivity Control: There is no option for users to adjust sensitivity, which limits accessibility and practicality for different environments and use cases.
Additional Context
The primary issue is that the voice input system defeats its own purpose. It’s meant to free up the user’s hands for multitasking (e.g., while exercising, cooking, or cleaning), but excessive sensitivity forces the user to remain completely still to avoid interruptions. This compromises the core utility of voice commands. It would be ideal if the system could be fine-tuned to better handle normal noise in everyday environments while still providing accurate responses.