New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Adds TTS to announcements made by the Captain and silicons #72300
Conversation
will this use the same TTS as that one testmerge? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
PR needs more documentation in the PR body about the TTS engine used. Website, a non-generic name (tts
, the name of the python package is too generic and not googleable), etc
PR needs a documentation file that includes links to the documentation of the tts engine. Including the code documentation.
PR needs to specify in the pr body rather or not the tts package calls out to another 3rd party service or generates it locally.
no, that was using a third party. |
This comment was marked as off-topic.
This comment was marked as off-topic.
This comment was marked as off-topic.
This comment was marked as off-topic.
This was really good! Could you at least tell us what happened? |
lost interest in working on it, it was practically feature complete but I was waiting on goof to finish training his dataset but it never really got to a point where it sounded good enough to test on the servers. |
That's fair enough. |
A shame. Maybe it'd be worth making in a way smaller scale exclusively for AI vox, but I don't know if you're interested in that |
The issues regarding it weren't dealbreakers nor impossible to fix, it's just that they took effort |
Hell yeah, we're back babyyyyy |
This reminds me of when we outsourced to that AI website. Those were good times. Glad something similar is being implemented. |
this is a very non-visible PR at the absolute bottom of the list and a lot of the technical grievances that were addressed in the comments here no longer apply due to the infrequent nature of announcements- let alone cover an entirely different subject body, making some of the feedback given pre-rename feel a bit odd would you kindly make a new PR such that it gains more visibility/traction from interested parties and not linger down here in the bowels of the PR list |
About The Pull Request
TTS currently can't handle every client having their own voice, so it's been limited to announcements made by the Captain and silicon players.
In the future, if we get a GPU server, it may become a more viable option to implement every client having their own voice because GPUs are great at concurrency.
It's all handled via python http requests to a local server. Docker is required to set up, but the container can be held on a separate linux server as it's only used to process text into audio and send it back via http requests.
TTS engine used in python script:
VITS: https://arxiv.org/pdf/2106.06103
coqui: https://github.com/coqui-ai/TTS
Base image is debian.
This is all handled locally. There are no calls to a third-party service.
Why It's Good For The Game
TTS is cool.
Changelog
🆑 Watermelon914, Iamgoofball, MrStonedOne
add: Adds TTS to announcements made by the Captain and silicon players.
/:cl: