Documentation bug TTS openedai speech #150
Description
Documentation Bug Report
Documentation needs an update for text to speech setup.
Description
The instructions for enabling Text To Speech (TTS) need updating.
I tried to get the openedai speech docker image working with open-webui by following the instructions here : https://docs.openwebui.com/tutorial/openedai-speech-integration without any luck, receiving connection errors. After checking through the openedai speech logs, I noticed that the voice being called was wrong and did not match the voice settings under Admin Panel -> Settings -> Audio -> TTS Voice.
After some fiddling:
The option under Settings -> Audio -> Set Voice needs to match the voice under the Admin Panel -> Settings -> Audio -> TTS Voice.
For example:
Admin Panel -> Settings -> Audio -> TTS Voice : Fable
Needs to match
Settings -> Audio -> Set Voice : Fable
Bug Summary:
Out of the box with a new install the instructions as they stand probably work, I wouldn't know because I messed around with a lot of settings trying to get voice working before realising the issue.
Steps to Reproduce:
Set different voices for the two different TTS voice settings under admin panel settings and setting.
Expected Behavior:
A connection error is reported if the voice settings are different.
Actual Behavior:
A connection error is reported if the voice settings are different.
Environment
-
Open WebUI Version: [Latest, no idea how to find the version]
-
Ollama (if applicable): [Not relevant]
-
Operating System: [Debian Bookworm]
-
Browser (if applicable): [not relevant,, but I was using Firefox]
Reproduction Details
Confirmation:
- I have read and followed all the instructions provided in the README.md.
- I am on the latest version of both Open WebUI and Ollama.
- I have included the browser console logs.
- [x ] I have included the Docker container logs.
Logs and Screenshots
Browser Console Logs:
[Include relevant browser console logs, if applicable]
Docker Container Logs:
openedai-speech log example:
INFO: 172.17.0.1:42200 - "POST /v1/audio/speech HTTP/1.1" 400 Bad Request
2024-07-17 09:19:42.245 | INFO | openedai:openai_statuserror_handler:106 - BadRequestError(message="Error loading voice: English (Received Pronunciation)+klatt4, KeyError: 'English (Received Pronunciation)+klatt4'", code=400, param=voice)
Example of correct settings.
Screenshots (if applicable):
**Admin settings -> Audio **
Settings Menu
Settings Menu -> Audio
Installation Method
Docker installation for openweb ui
Docker installation for openedai-speech
Additional Information
[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]
Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!