[GH-ISSUE #23017] feat: Support for Qwen/Qwen3-ASR-0.6B Model #19868

Closed
opened 2026-04-20 02:23:43 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @KushtrimVisoka on GitHub (Mar 25, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/23017

Check Existing Issues

  • I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

  • I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

Problem Description

OpenWebUI currently supports Whisper for ASR, but does not support the Qwen/Qwen3-ASR-0.6B model. This limits the ability to use alternative ASR models within the same interface.

Desired Solution you'd like

Add support for Qwen/Qwen3-ASR-0.6B as an additional ASR backend option in OpenWebUI, compatible with the existing audio input pipeline.

Alternatives Considered

Continue using Whisper as the only supported ASR backend.

Additional Context

Qwen/Qwen3-ASR-0.6B is a recently available ASR model that could be a useful alternative option for users.

Originally created by @KushtrimVisoka on GitHub (Mar 25, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/23017 ### Check Existing Issues - [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request. ### Verify Feature Scope - [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions. ### Problem Description OpenWebUI currently supports Whisper for ASR, but does not support the Qwen/Qwen3-ASR-0.6B model. This limits the ability to use alternative ASR models within the same interface. ### Desired Solution you'd like Add support for Qwen/Qwen3-ASR-0.6B as an additional ASR backend option in OpenWebUI, compatible with the existing audio input pipeline. ### Alternatives Considered Continue using Whisper as the only supported ASR backend. ### Additional Context Qwen/Qwen3-ASR-0.6B is a recently available ASR model that could be a useful alternative option for users.
Author
Owner

@hdnh2006 commented on GitHub (Mar 30, 2026):

I think if you deploy Qwen3-ASR with an OpenAI compatible API, you will be able to connect it.

<!-- gh-comment-id:4154174602 --> @hdnh2006 commented on GitHub (Mar 30, 2026): I think if you deploy Qwen3-ASR with an OpenAI compatible API, you will be able to connect it.
Author
Owner

@Classic298 commented on GitHub (Apr 15, 2026):

As @hdnh2006 mentioned, this is already supported. Set the STT engine to "openai", point the base URL to your Qwen3-ASR server (served via vLLM, LiteLLM, or any OpenAI-compatible wrapper), and set the model name accordingly. The OpenAI-compatible STT engine handles the standard /audio/transcriptions endpoint.

No additional integration is needed for this. Closing as already supported.

<!-- gh-comment-id:4254936402 --> @Classic298 commented on GitHub (Apr 15, 2026): As @hdnh2006 mentioned, this is already supported. Set the STT engine to "openai", point the base URL to your Qwen3-ASR server (served via vLLM, LiteLLM, or any OpenAI-compatible wrapper), and set the model name accordingly. The OpenAI-compatible STT engine handles the standard /audio/transcriptions endpoint. No additional integration is needed for this. Closing as already supported.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#19868