Update OpenAI TTS config to allow a custom BaseURL allowing for any TTS engine with a compatible API #2466
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
639788f to
99af124
Compare
99af124 to
bdf3fb8
Compare
Member
|
Moved to #2487 (youll still have PR credit) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request Type
Relevant Issues
resolves #xxx
What is in this change?
This adds an input field for a custom BaseURL for the OpenAI TTS endpoint when selecting OpenAI as a TTS provider.
Since OpenAI has become an industry standard many tools have taken to mirroring their API for ease of integration.
With this change it allows for a much richer choice of options to use as a TTS provider.
I tested it using AllTalk_TTS's OpenAI speech endpoint and it works wonderfully.
Developer Validations
I ran
yarn lintfrom the root of the repo & committed changes[ x] Relevant documentation has been updated
couldn't find any relevant docs, but it is notated in the env comments
[ x] I have tested my code functionality
[ x] Docker build succeeds locally
In order to debug this, I needed to get the frontend/server/collector all working since the docker takes a VERY long time on the production-build 3/3 chown step. There has got to be a way to speed that up. Also, when running the servers independently, it doesn't save the config in any .env file so with every restart I had to set it up again, don't know what I missed there. I was also running it under WSL ubuntu, so that was it's own pita, my dev machine is a MBP, but only my PC can run the models :/