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

Picovoice account gets deleted #19

Open
RetoHB opened this issue Nov 26, 2023 · 4 comments
Open

Picovoice account gets deleted #19

RetoHB opened this issue Nov 26, 2023 · 4 comments

Comments

@RetoHB
Copy link

RetoHB commented Nov 26, 2023

Picovoice keeps deleting my accounts. This already happened twice, every time about a day after I opened the account.
Anybody having the same issue?

"An account registered with 'xxxxx' has been removed by the Picovoice Audit System. Accounts can be removed in cases of Picovoice Terms of Use violations, such as suspicious activities, creating multiple accounts, or providing false information."

@DevMiser
Copy link
Owner

This has never happened to me.

You may want to try to contact Picovoice directly. I think their email is hello@picovoice.ai.

@RetoHB
Copy link
Author

RetoHB commented Nov 26, 2023

I tried that, but they are not responding on that email.

@EA914
Copy link

EA914 commented Apr 16, 2024

You know, for speech to text you can use OpenAI's whisper model. This would be better in my opinion so you only are hitting one API endpoint.

Check my github repository for a code example. I suggest using this for speech-to-text and transcribe your prompt, send to ChatGPT to get a response, then use OpenAI again for text-to-speech!

@DevMiser
Copy link
Owner

Yes, OpenAI's Whisper can be used for the speech to text. However, you still need to have wake word capability for DaVinci, which Whisper does not provide. DaVinci currently uses Picovoice Porcupine for detecting its name. Rhasspy may provide another wake word option if you cannot or do not want to use Picovoice. I prefer the responsiveness of Picovoice for both wake word and speech-to-text on a Raspberry Pi. And the PicoVoice options are currently free of charge for hobbyists as opposed to OpenAI's now charge per use plan. If you also want to use OpenAI for text-to-speech, you can use the DaVinciAltVoice.py version on this repository.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants