[GH-ISSUE #7890] Pass audio files directly to LLM instead of passing a transcript #53588

New Issue

GiteaMirror · 2026-05-05T14:55:20-05:00

GiteaMirror commented

2026-05-05 14:55:20 -05:00

Originally created by @Simon-Stone on GitHub (Dec 16, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7890

Is your feature request related to a problem? Please describe.
With multimodal LLMs that can process audio now widely available, it would be very helpful to pass an audio file directly to the model, similar to how images can now be sent as part of a message.

Describe the solution you'd like
When uploading an audio file, a dialog popup should ask whether the file should be transcribed to text or passed as context directly.

Originally created by @Simon-Stone on GitHub (Dec 16, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/7890 **Is your feature request related to a problem? Please describe.** With multimodal LLMs that can process audio now widely available, it would be very helpful to pass an audio file directly to the model, similar to how images can now be sent as part of a message. **Describe the solution you'd like** When uploading an audio file, a dialog popup should ask whether the file should be transcribed to text or passed as context directly.

GiteaMirror closed this issue

2026-05-05 14:55:21 -05:00

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#53588