I've been experimenting with conversing through audio recordings, and while the model successfully transcribes the recordings into Hindi text, the generated responses are limited to a single phrase - 'AIAI' - with subpar pronunciation.
Considering a paid subscription seems futile at this point, as the model requires significant improvement. Although I appreciate the inclusion of Hindi conversations, I question its adaptability.
Furthermore, the voice actions lack neutrality, sounding somewhat unnatural. Ideally, conversational voice models should be pleasing and soothing. I suggest exploring better voice models to enhance the overall experience.
Please authenticate to join the conversation.
In Review
π Bug Reports
Over 1 year ago
Get notified by email when there are changes.
In Review
π Bug Reports
Over 1 year ago
Get notified by email when there are changes.