OpenWebUI/docs
1
0
Fork 0
mirror of https://github.com/open-webui/docs synced 2025-05-20 03:08:56 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Update openai-edge-tts-integration.md

Browse Source
This commit is contained in:
Travis Van Nimwegen 2024-10-20 15:14:57 -04:00 committed by GitHub
parent 3f88c7e80d
commit df446fa8ac
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 28 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
docs/tutorials/integrations/openai-edge-tts-integration.md
View File

@ -3,7 +3,7 @@ sidebar_position: 18
title: "Edge TTS"
---
# Integrating `openai-edge-tts` with Open WebUI
# Integrating `openai-edge-tts` 🗣️ with Open WebUI
## What is `openai-edge-tts`, and how is it different from `openedai-speech`?
@ -13,7 +13,7 @@ Similar to [openedai-speech](https://github.com/matatonic/openedai-speech), [ope
`openai-edge-tts` is a simpler option that uses a Python package called `edge-tts` to generate the audio.
`edge-tts` leverages the Edge browser's free "Read Aloud" feature to emulate a request to Microsoft / Azure in order to receive very high quality text-to-speech for free.
`edge-tts` ([repo](https://github.com/rany2/edge-tts)) leverages the Edge browser's free "Read Aloud" feature to emulate a request to Microsoft / Azure in order to receive very high quality text-to-speech for free.
## Requirements
@ -21,7 +21,7 @@ Similar to [openedai-speech](https://github.com/matatonic/openedai-speech), [ope
- Open WebUI running
- ffmpeg installed (required for audio format conversion and playback speed adjustments)
## Quick start
## ⚡️ Quick start
The simplest way to get started without having to configure anything is to run the command below
@ -47,9 +47,15 @@ The default API key is the string `your_api_key_here`. You do not have to change
See the [Usage](#usage) section for request examples.
# Please ⭐️ star the repo on GitHub if you find [OpenAI Edge TTS](https://github.com/travisvn/openai-edge-tts) useful
:::tip
You can define the environment variables directly in the `docker run` command. See [Quick Config for Docker](#-quick-config-for-docker) below.
:::
## Alternative Options
### Running with Python
### 🐍 Running with Python
If you prefer to run this project directly with Python, follow these steps to set up a virtual environment, install dependencies, and start the server.
@ -176,10 +182,25 @@ curl -X POST http://localhost:5050/v1/audio/speech \
##### Additional Endpoints
- **GET /v1/models**: Lists available TTS models.
- **GET /v1/voices**: Lists `edge-tts` voices for a given language / locale.
- **GET /v1/voices/all**: Lists all `edge-tts` voices, with language support information.
- **POST/GET /v1/models**: Lists available TTS models.
- **POST/GET /v1/voices**: Lists `edge-tts` voices for a given language / locale.
- **POST/GET /v1/voices/all**: Lists all `edge-tts` voices, with language support information.
## 🐳 Quick Config for Docker
You can configure the environment variables in the command used to run the project
```bash
docker run -d -p 5050:5050 \
-e API_KEY=your_api_key_here \
-e PORT=5050 \
-e DEFAULT_VOICE=en-US-AndrewNeural \
-e DEFAULT_RESPONSE_FORMAT=mp3 \
-e DEFAULT_SPEED=1.0 \
-e DEFAULT_LANGUAGE=en-US \
-e REQUIRE_API_KEY=True \
travisvn/openai-edge-tts:latest
```
## Additional Resources