OpenWebUI/docs
1
0
Fork 0
mirror of https://github.com/open-webui/docs synced 2025-05-21 11:46:15 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Update openai-edge-tts-integration.md

Browse Source 
Updated screenshot to show configuration with broad compatibility, updated information about ffmpeg optionality, added link to Discord for support, and updated speed to its new default of 1.2
This commit is contained in:
Travis Van Nimwegen 2024-12-03 19:05:38 -05:00 committed by GitHub
parent 7126e3a9fa
commit 99e69d2d27
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docs/tutorials/integrations/openai-edge-tts-integration.md
View File

@ -24,7 +24,7 @@ Similar to [openedai-speech](https://github.com/matatonic/openedai-speech), [ope
- Docker installed on your system - Docker installed on your system
- Open WebUI running - Open WebUI running
- ffmpeg installed (required for audio format conversion and playback speed adjustments) - ffmpeg (Optional - Only required if opting to not use `mp3` format)
## ⚡️ Quick start ## ⚡️ Quick start
@ -42,7 +42,7 @@ This will run the service at port 5050 with all the default configs
- Set your TTS Settings to match the screenshot below - Set your TTS Settings to match the screenshot below
- _Note: you can specify the TTS Voice here_ - _Note: you can specify the TTS Voice here_
![Screenshot of Open WebUI Admin Settings for Audio adding the correct endpoints for this project](https://utfs.io/f/MMMHiQ1TQaBoQ2AnPhUlTDGtR4B2v7E9JZN1PU5nAseoaXIc) ![Screenshot of Open WebUI Admin Settings for Audio adding the correct endpoints for this project](https://utfs.io/f/MMMHiQ1TQaBo9GgL4WcUbjSRlqi86sV3TXh47KYBJCkdQ20M)
:::info :::info
The default API key is the string `your_api_key_here`. You do not have to change that value if you do not need the added security. The default API key is the string `your_api_key_here`. You do not have to change that value if you do not need the added security.
@ -67,7 +67,7 @@ If you prefer to run this project directly with Python, follow these steps to se
#### 1. Clone the Repository #### 1. Clone the Repository
```bash ```bash
git clone https://github.com/your-username/openai-edge-tts.git git clone https://github.com/travisvn/openai-edge-tts.git
cd openai-edge-tts cd openai-edge-tts
``` ```
@ -103,7 +103,7 @@ PORT=5050
DEFAULT_VOICE=en-US-AndrewNeural DEFAULT_VOICE=en-US-AndrewNeural
DEFAULT_RESPONSE_FORMAT=mp3 DEFAULT_RESPONSE_FORMAT=mp3
DEFAULT_SPEED=1.0 DEFAULT_SPEED=1.2
DEFAULT_LANGUAGE=en-US DEFAULT_LANGUAGE=en-US
@ -140,7 +140,7 @@ Generates audio from the input text. Available parameters:
- **model** (string): Set to "tts-1" or "tts-1-hd" (default: `"tts-1"`). - **model** (string): Set to "tts-1" or "tts-1-hd" (default: `"tts-1"`).
- **voice** (string): One of the OpenAI-compatible voices (alloy, echo, fable, onyx, nova, shimmer) or any valid `edge-tts` voice (default: `"en-US-AndrewNeural"`). - **voice** (string): One of the OpenAI-compatible voices (alloy, echo, fable, onyx, nova, shimmer) or any valid `edge-tts` voice (default: `"en-US-AndrewNeural"`).
- **response_format** (string): Audio format. Options: `mp3`, `opus`, `aac`, `flac`, `wav`, `pcm` (default: `mp3`). - **response_format** (string): Audio format. Options: `mp3`, `opus`, `aac`, `flac`, `wav`, `pcm` (default: `mp3`).
- **speed** (number): Playback speed (0.25 to 4.0). Default is `1.0`. - **speed** (number): Playback speed (0.25 to 4.0). Default is `1.2`.
:::tip :::tip
You can browse available voices and listen to sample previews at [tts.travisvn.com](https://tts.travisvn.com) You can browse available voices and listen to sample previews at [tts.travisvn.com](https://tts.travisvn.com)
@ -205,7 +205,7 @@ docker run -d -p 5050:5050 \
-e PORT=5050 \ -e PORT=5050 \
-e DEFAULT_VOICE=en-US-AndrewNeural \ -e DEFAULT_VOICE=en-US-AndrewNeural \
-e DEFAULT_RESPONSE_FORMAT=mp3 \ -e DEFAULT_RESPONSE_FORMAT=mp3 \
-e DEFAULT_SPEED=1.0 \ -e DEFAULT_SPEED=1.2 \
-e DEFAULT_LANGUAGE=en-US \ -e DEFAULT_LANGUAGE=en-US \
-e REQUIRE_API_KEY=True \ -e REQUIRE_API_KEY=True \
travisvn/openai-edge-tts:latest travisvn/openai-edge-tts:latest
@ -215,6 +215,8 @@ docker run -d -p 5050:5050 \
For more information on `openai-edge-tts`, you can visit the [GitHub repo](https://github.com/travisvn/openai-edge-tts) For more information on `openai-edge-tts`, you can visit the [GitHub repo](https://github.com/travisvn/openai-edge-tts)
For direct support, you can visit the [Voice AI & TTS Discord](https://discord.gg/GkFbBCBqJ6)
## 🎙️ Voice Samples ## 🎙️ Voice Samples
[Play voice samples and see all available Edge TTS voices](https://tts.travisvn.com/) [Play voice samples and see all available Edge TTS voices](https://tts.travisvn.com/)