Skip to content
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

websocket implementation of elevenlabs #1586

Merged
merged 6 commits into from
Feb 3, 2025
Merged

Conversation

aalghooneh
Copy link
Contributor

  • **What kind of change does this PR introduce? feature

  • **Why was this change needed? to improve speed for long responses

  • Other information:#1585

Copy link

vercel bot commented Jan 16, 2025

@aalghooneh is attempting to deploy a commit to the Arc53 Team on Vercel.

A member of the Team first needs to authorize it.

@aalghooneh
Copy link
Contributor Author

@dartpain could you give this a look?

Copy link
Collaborator

@ManishMadan2882 ManishMadan2882 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@aalghooneh there is an error in importing base class in tts/elevenlabs.py, just check how we import it in GoogleTTS.

@aalghooneh
Copy link
Contributor Author

aalghooneh commented Jan 28, 2025

@aalghooneh there is an error in importing base class in tts/elevenlabs.py, just check how we import it in GoogleTTS.

It should be okay now, could you check again ? @ManishMadan2882

Copy link
Collaborator

@ManishMadan2882 ManishMadan2882 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@aalghooneh After updating the endpoint /api/tts to use the ElevenlabsTTS, I get this error on the frontend
{ "error": "cannot unpack non-iterable NoneType object", "success": false }

The output.mp3 is also not playable

@aalghooneh
Copy link
Contributor Author

@ManishMadan2882 the output.mp3 was something for me to check the streaming and test the api, you can run the elevenlabs.py separately to see that working.

let me look into it tonight, now I am away from workspace

@aalghooneh
Copy link
Contributor Author

@ManishMadan2882 this works fine for me, did you set these variables in the code before trying?
self.api_key = 'ELEVENLABS_API_KEY'# here you should put your api key
self.model = "eleven_flash_v2_5"
self.voice = "VOICE_ID" # this is the hash code for the voice not the name!
self.write_audio = 1
the voice_id should be a hash, and elevenlabs_api_key should be a valid elevenlabs api

@ManishMadan2882
Copy link
Collaborator

@aalghooneh worked when the application/tts/elevenlabs.tts was only executed.

Copy link
Collaborator

@ManishMadan2882 ManishMadan2882 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @aalghooneh !

@aalghooneh
Copy link
Contributor Author

thanks @ManishMadan2882,

it also needs authorization to deploy Vercel-docsgpt so it could merge.

@aalghooneh
Copy link
Contributor Author

@dartpain , @ManishMadan2882 , ?

@dartpain dartpain merged commit 9583095 into arc53:main Feb 3, 2025
2 of 3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
application Application
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants