[PR #248] [MERGED] Create openai-edge-tts-integration.md #363

New issue

Closed

opened 2026-10-18 14:11:27 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:11:27 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/docs/pull/248
Author: @travisvn
Created: 10/19/2024
Status: ✅ Merged
Merged: 10/19/2024
Merged by: @tjbck

Base: main ← Head: patch-1

📝 Commits (2)

a5e4a7f Create openai-edge-tts-integration.md
f31c49c Update openai-edge-tts-integration.md to fix admonition syntax

📊 Changes

1 file changed (+187 additions, -0 deletions)

View changed files

➕ docs/tutorials/integrations/openai-edge-tts-integration.md (+187 -0)

📄 Description

This PR adds new documentation to guide users on integrating the openai-edge-tts text-to-speech service with Open WebUI. The document includes:

Overview of openai-edge-tts: Describes how it differs from openedai-speech and its reliance on the Edge browser's Read Aloud feature for generating high-quality TTS.
Requirements and Setup: Lists prerequisites like Docker, Open WebUI, and ffmpeg, along with step-by-step instructions for running the service via Docker or Python.
Configuration with Open WebUI: Provides guidance on setting up the Admin Panel for audio settings, including voice configuration and API key usage.
Usage and Endpoints: Details the primary API endpoint for generating speech, along with additional endpoints for listing available models and voices.
Quick start examples: Includes code snippets for making API requests using curl.

This documentation aims to help users quickly integrate and use openai-edge-tts as a TTS option within Open WebUI.

_{🔄 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/docs/pull/248 **Author:** [@travisvn](https://github.com/travisvn) **Created:** 10/19/2024 **Status:** ✅ Merged **Merged:** 10/19/2024 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `main` ← **Head:** `patch-1` --- ### 📝 Commits (2) - [`a5e4a7f`](https://github.com/open-webui/docs/commit/a5e4a7fbf2f0bc9f0fa1253e9dd6960ec4704d47) Create openai-edge-tts-integration.md - [`f31c49c`](https://github.com/open-webui/docs/commit/f31c49c6828dd34b325c4efc6f3a8fe9f7a6f56d) Update openai-edge-tts-integration.md to fix admonition syntax ### 📊 Changes **1 file changed** (+187 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `docs/tutorials/integrations/openai-edge-tts-integration.md` (+187 -0) </details> ### 📄 Description This PR adds new documentation to guide users on integrating the `openai-edge-tts` text-to-speech service with Open WebUI. The document includes: - **Overview of `openai-edge-tts`**: Describes how it differs from `openedai-speech` and its reliance on the Edge browser's Read Aloud feature for generating high-quality TTS. - **Requirements and Setup**: Lists prerequisites like Docker, Open WebUI, and ffmpeg, along with step-by-step instructions for running the service via Docker or Python. - **Configuration with Open WebUI**: Provides guidance on setting up the Admin Panel for audio settings, including voice configuration and API key usage. - **Usage and Endpoints**: Details the primary API endpoint for generating speech, along with additional endpoints for listing available models and voices. - **Quick start examples**: Includes code snippets for making API requests using `curl`. This documentation aims to help users quickly integrate and use `openai-edge-tts` as a TTS option within Open WebUI. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 14:11:27 +00:00