[GH-ISSUE #18466] issue: "Instant Auto-Send After Voice Transcription" setting has no effect - it's always off #34134

New Issue

2026-04-25T08:03:44-05:00

GiteaMirror commented

2026-04-25 08:03:44 -05:00

Originally created by @peter-ch on GitHub (Oct 20, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18466

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I am using the latest version of Open WebUI.

Installation Method

Pip Install

Open WebUI Version

0.6.34

Ollama Version (if applicable)

No response

Operating System

Windows 11

Browser (if applicable)

Chrome, most recent

Confirmation

I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

When I stop speaking and click the blue icon to end recording, and the "Instant Auto-Send After Voice Transcription" is "On", the transcribed text has to be sent right away to the model.

Actual Behavior

But that never happens. On or Off, it doesn't matter, I always have to send the message myself by pressing Enter.

Steps to Reproduce

Setup voice input, use local whisper
Set the Instant Auto-Send After Voice Transcription to On
Input some audio. It won't be sent after transcription.

Logs & Screenshots

You have to believe me here, there are no errors and such things. Very easy to confirm.

Additional Information

No response

Originally created by @peter-ch on GitHub (Oct 20, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/18466 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Pip Install ### Open WebUI Version 0.6.34 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 ### Browser (if applicable) Chrome, most recent ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior When I stop speaking and click the blue icon to end recording, and the "Instant Auto-Send After Voice Transcription" is "On", the transcribed text has to be sent right away to the model. ### Actual Behavior But that never happens. On or Off, it doesn't matter, I always have to send the message myself by pressing Enter. ### Steps to Reproduce 1. Setup voice input, use local whisper 2. Set the Instant Auto-Send After Voice Transcription to On 3. Input some audio. It won't be sent after transcription. ### Logs & Screenshots You have to believe me here, there are no errors and such things. Very easy to confirm. ### Additional Information _No response_

GiteaMirror added the bug label 2026-04-25 08:03:44 -05:00

GiteaMirror closed this issue

2026-04-25 08:03:44 -05:00

GiteaMirror commented

2026-04-25 08:03:45 -05:00

@tjbck commented on GitHub (Oct 21, 2025):

Addressed in dev with 0a78ceef6dcc135fcfbad94c586a2f9bce4345fe!

@tjbck commented on GitHub (Oct 21, 2025): Addressed in dev with 0a78ceef6dcc135fcfbad94c586a2f9bce4345fe!

GiteaMirror commented

2026-04-25 08:03:46 -05:00

@peter-ch commented on GitHub (Oct 22, 2025):

Thanks!

@peter-ch commented on GitHub (Oct 22, 2025): Thanks!

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#34134