text-generation-webui
text-generation-webui copied to clipboard
Elevenlabs extension has a bug do not use it
Describe the bug
the elevenlabs extension sent the same request in a loop for each new token crated it sent a request to the api until the full answer was completed. I had a maximum of 200 tokens so it 😢blew all my months quota almost 15$ of tokens I just installed it to try it out but stupid me notice something was wrong and didn't stop it. I am not blaming anyone or being a Karen, the idea is great, but I have a couple of suggestions besides fixing the error, one I would like the character to still give me the answer in txt and second that it only produces the text first and then the audio if I like the answer or if I select to auto generate the audio that would be nice in an option. thanks
Is there an existing issue for this?
- [X] I have searched the existing issues
Reproduction
the elevenlabs extension
Screenshot

Logs
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
File "C:\Users\Uzr\anaconda3\envs\textgen\lib\asyncio\events.py", line 80, in _run
self._context.run(self._callback, *self._args)
File "C:\Users\Uzr\anaconda3\envs\textgen\lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
self._sock.shutdown(socket.SHUT_RDWR)
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
System Info
Win 10 no WSL
Nvidia RTX 3090
RAM 32GB
AMD Ryzen 7 1700
Add --no-stream. These tts extensions are not meant to be used with streaming.
A failsafe has been added to prevent something like this from happening again https://github.com/oobabooga/text-generation-webui/commit/a90f507abe0243949d2720a009283cc84d0e62ae
Thank you.