thank you for inspiring! I've noticed that "personality" thing is really key to make the conversation entertaining (none-flat). Don't have that polishes just yet, maybe how to use different modes? Don't have a good idea how to build this so that is it easy to navigate for the user. I've connected a power-bank to the raspberry pi now, to make the thing portable, and it seems to run for quite a while (however it is just the speech stuff, no motors just yet). I still have to work on the transcription precision, cause I noticed that what I am saying and what gpt4o receives as a text can differ too often by too much. Love your stuff!!!! Waiting for the next video(s)!
@Dufftata Thx so much for the support! I just posted my code on Github / LarrysWorkbench feel free to check it out. It seems like "Personality" is what turns GPT into "Floyd" and makes the project fun. Floyd's Personality comes from about 12 plaintext sentences. I think of it as his Long-Term Memory. The most important instruction is for him to keep his responses BRIEF, two sentences max. Regarding transcription - maybe check out your hardware. I feel like the Whisper API does a really good job when I give it a decent audio file to work with....
Thank you so much - that's absolutely great to hear! This whole project was originally designed to be kid-friendly, although it seems like it evolved a little bit. I don't make any money doing this, but comments like yours make it absolutely worthwhile. I've posted my source code at github.com/larrysworkbench. Keep in touch and let me know how your project goes!
thank you for inspiring! I've noticed that "personality" thing is really key to make the conversation entertaining (none-flat). Don't have that polishes just yet, maybe how to use different modes? Don't have a good idea how to build this so that is it easy to navigate for the user. I've connected a power-bank to the raspberry pi now, to make the thing portable, and it seems to run for quite a while (however it is just the speech stuff, no motors just yet). I still have to work on the transcription precision, cause I noticed that what I am saying and what gpt4o receives as a text can differ too often by too much.
Love your stuff!!!! Waiting for the next video(s)!
@Dufftata Thx so much for the support! I just posted my code on Github / LarrysWorkbench feel free to check it out. It seems like "Personality" is what turns GPT into "Floyd" and makes the project fun. Floyd's Personality comes from about 12 plaintext sentences. I think of it as his Long-Term Memory. The most important instruction is for him to keep his responses BRIEF, two sentences max.
Regarding transcription - maybe check out your hardware. I feel like the Whisper API does a really good job when I give it a decent audio file to work with....
Thanks very much! I always look forward to your next video
Fantastic! I'm trying to post about one a week.
Let me know what you'd like to see in particular
I have been eager to do this project with my son this summer. I hope the next video comes soon :-)
Thank you so much - that's absolutely great to hear! This whole project was originally designed to be kid-friendly, although it seems like it evolved a little bit.
I don't make any money doing this, but comments like yours make it absolutely worthwhile.
I've posted my source code at github.com/larrysworkbench. Keep in touch and let me know how your project goes!
Love the videos man wanna make my own talking robot.
Go for it (!)
interesting
Thank you.. check out some of Floyd’s other videos
How can i contact you? For some doubts
Thanks for reaching out. The easiest way is to leave me messages here -
Did you ever get into a tickle contest and lose on purpose?? hehe😉
Floyd's not ticklish, but I don't think he particularly enjoys being picked up......