github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-02 06:39:02 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[PR #12727] [MERGED] feat: add Azure AI Speech STT provider #94047

New Issue
Closed
opened 2026-05-15 20:00:08 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-15 20:00:08 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/12727
Author: @decent-engineer-decent-datascientist
Created: 4/10/2025
Status: ✅ Merged
Merged: 4/10/2025
Merged by: @tjbck

Base: dev ← Head: main

📝 Commits (1)

  • 9a55257 feat: add Azure AI Speech STT provider

📊 Changes

4 files changed (+186 additions, -9 deletions)

View changed files

📝 backend/open_webui/config.py (+18 -0)
📝 backend/open_webui/main.py (+7 -0)
📝 backend/open_webui/routers/audio.py (+115 -0)
📝 src/lib/components/admin/Settings/Audio.svelte (+46 -9)

📄 Description

  • Add Azure STT configuration variables for API key, region and locales
  • Implement Azure STT transcription endpoint with 200MB file size limit
  • Update Audio settings UI to include Azure STT configuration fields
  • Handle Azure API responses and error cases consistently

Pull Request Checklist

  • Target branch: Please verify that the pull request targets the dev branch.
  • Description: Add Azure AI Speech as a new Speech-to-Text provider, enabling high-quality speech recognition with support for multiple languages.
  • Changelog: Added below
  • Documentation: Documentation updates needed for Azure STT configuration
  • Dependencies: New dependency on Azure AI Speech REST API
  • Testing: Manual testing completed for transcription functionality
  • Code review: Self-review completed
  • Prefix: Using feat prefix for new feature addition

Changelog Entry

Description

Add Azure AI Speech as a new Speech-to-Text (STT) provider, offering enhanced transcription capabilities with support for multiple languages and larger file sizes up to 200MB. This integration provides users with an additional high-quality option for speech recognition.

Added

  • Azure STT configuration variables for API key, region and locales
  • Azure STT transcription endpoint implementation with 200MB file size support
  • Audio settings UI components for Azure configuration
  • Error handling and response processing for Azure API

Changed

  • Updated Audio settings UI to include Azure STT provider option
  • Enhanced STT provider selection to include Azure AI Speech

Dependencies

  • Azure AI Speech REST API (2024-11-15 version)

Additional Information

The Azure AI Speech integration provides several advantages:

  • Support for larger audio files (up to 200MB)
  • Multiple language support through locale configuration
  • Auto-language detection when no locales specified
  • Enterprise-grade speech recognition quality

Configuration

To use Azure STT:

  1. Select "Azure AI Speech" as the STT provider in Audio settings
  2. Enter your Azure API key and region
  3. Optionally specify language locales (e.g., "en-US,ja-JP") or leave blank for auto-detection

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/12727 **Author:** [@decent-engineer-decent-datascientist](https://github.com/decent-engineer-decent-datascientist) **Created:** 4/10/2025 **Status:** ✅ Merged **Merged:** 4/10/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `dev` ← **Head:** `main` --- ### 📝 Commits (1) - [`9a55257`](https://github.com/open-webui/open-webui/commit/9a55257c5b7557c0658b6c5f613d2012b4e678d1) feat: add Azure AI Speech STT provider ### 📊 Changes **4 files changed** (+186 additions, -9 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+18 -0) 📝 `backend/open_webui/main.py` (+7 -0) 📝 `backend/open_webui/routers/audio.py` (+115 -0) 📝 `src/lib/components/admin/Settings/Audio.svelte` (+46 -9) </details> ### 📄 Description - Add Azure STT configuration variables for API key, region and locales - Implement Azure STT transcription endpoint with 200MB file size limit - Update Audio settings UI to include Azure STT configuration fields - Handle Azure API responses and error cases consistently # Pull Request Checklist - [x] **Target branch:** Please verify that the pull request targets the `dev` branch. - [x] **Description:** Add Azure AI Speech as a new Speech-to-Text provider, enabling high-quality speech recognition with support for multiple languages. - [x] **Changelog:** Added below - [x] **Documentation:** Documentation updates needed for Azure STT configuration - [x] **Dependencies:** New dependency on Azure AI Speech REST API - [x] **Testing:** Manual testing completed for transcription functionality - [x] **Code review:** Self-review completed - [x] **Prefix:** Using `feat` prefix for new feature addition # Changelog Entry ### Description Add Azure AI Speech as a new Speech-to-Text (STT) provider, offering enhanced transcription capabilities with support for multiple languages and larger file sizes up to 200MB. This integration provides users with an additional high-quality option for speech recognition. ### Added - Azure STT configuration variables for API key, region and locales - Azure STT transcription endpoint implementation with 200MB file size support - Audio settings UI components for Azure configuration - Error handling and response processing for Azure API ### Changed - Updated Audio settings UI to include Azure STT provider option - Enhanced STT provider selection to include Azure AI Speech ### Dependencies - Azure AI Speech REST API (2024-11-15 version) ### Additional Information The Azure AI Speech integration provides several advantages: - Support for larger audio files (up to 200MB) - Multiple language support through locale configuration - Auto-language detection when no locales specified - Enterprise-grade speech recognition quality ### Configuration To use Azure STT: 1. Select "Azure AI Speech" as the STT provider in Audio settings 2. Enter your Azure API key and region 3. Optionally specify language locales (e.g., "en-US,ja-JP") or leave blank for auto-detection --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-05-15 20:00:08 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#94047