Thanks for the train, sadly I can't give any input on the project since I've avoided any type of voice recognition interface my whole life, I just don't like talking to computers if I can do something via a GUI, dedicated physical buttons, or even typing commands. Every time I accidentally activate the gemini thing on my phone I remain completely silent so it won't hear any command so I can close it down quicker, whoever decided to map the headphones button long press to it is evil, I need that button to control the media player.
Comment has been collapsed.
+1 can relate to that lol, rather just type something out instead of waking up people in the house at 3am.
Comment has been collapsed.
I don't know how hard could it be, but can a new voice be trained from your own voice?
Comment has been collapsed.
Have a very impressed bump. I wouldn't have the first idea what you are doing, but it seems you are. Let's hope the painkillers continue working for you.
Is your dental ordeal over with that surgery or do you have to have some more work done?
Also, remember: Gum shield. And keep the bill and details of the procedure so you can show your son why he doesn't get a birthday present for his 18th. 🤣
Comment has been collapsed.
Lol oh I won't be forgetting this anytime soon and I guarantee Tobias will hear all about it forever. As soon as he is old enough not to take it to heart, the crap won't stop being piled on ^^
For now I'm done with operations unless something goes wrong, then well, I would have to get it removed and have a jaw bone graft done before trying again. But at the cost, I will probably just stay hillbilly forever ^^
Comment has been collapsed.
good luck on your project - unfortunately I have nothing to add!
Comment has been collapsed.
Even simple choice of female/male voice will be big I think ;) good luck
Comment has been collapsed.
Wow. Painkillers seem to be working for you. I am notoriously resistant to them (despite not having taken much) so the last time I had dental surgery, I was more high on pain than anything and the painkillers I took just made me totally useless on a keyboard (let alone handling a knife).
I can't imagine taking on AI while that was happening!
I can't really think of any feature today because I literally had 3 hours of sleep but I'll put my overcooked brain to it once I managed to catch some Zzzzs
I'll ask my sister for help as she has interest in AI conversation and worked on some chatbot a looooong time ago for a luxury brand website back when they had to program responses because AI didn't exist lol. She may have an idea or two.
Comment has been collapsed.
Thanks for the train! Unfortunately I don't have any new ideas for you.
Comment has been collapsed.
Not skilled enough in that domain to suggest ideas, but have some congratulatory bump
Comment has been collapsed.
Oh man, the last serious painkiller I had made me super nauseated, which was bad because it was also for dental work. "Take with food and milk" "don't eat for hours". These instructions don't work together, thanks doc. Glad you're headed the right direction and hope it stays that way.
I always had a fondness for the autogenerated computer voices. You should have a voice that sounds like the War Games movie or such. Or those command-line speech synthesizers in Linux.
Comment has been collapsed.
I'll start by saying thank you for the train! I'm not even at the end yet and I'm already out of points.
It's unclear from your screenshots what your app is trying to achieve, or at least what it's trying to achieve that is not already possible using some other apps. Or did you build it because what's out there simply doesn't work as well?
Comment has been collapsed.
I didn't build it for any real purpose. Originally I was making my AI graphics generator as I had an idea ( I still like idea as it's unique so I am not saying what it was lol) but then my friend asked me to make a light weight AI for his project.
So in turn I built this to be 100% off-line standalone. Does not require or connect via the internet at all. Everything is based and stored locally on your own PC, using your own hardware to do so. In turn you could essentially give it control of, and be able to manipulate or access, your own files. That is to say I take it that far.
For now, it's simply an AI voice program that quite literally you can hold a conversation with and as I said is completely off-line and currently using about 3gb of Hard Drive space.
Comment has been collapsed.
Alright, I didn't quite catch the stand-alone part the first time around. I guess it's a much bigger accomplishment if that's the case.
I still don't see a use-case apart from using it offline for some reason. But that's probably because I don't really see a use-case for AI as it stands 😅
Comment has been collapsed.
Hahaha don't get me wrong there is no real accomplishment here. I was going to make a train of GAs and normally I'll write a fantasy choose your own adventure, or a puzzle, a maze like i did ages ago with full set of train lines and story involved.
This time, i had nothing. I have spent my time writing about 1500 odd lines of script for this AI, I haven't made any form or puzzle etc. So, all I could post about is this. ^^
Comment has been collapsed.
1,143 Comments - Last post 20 minutes ago by sensualshakti
190 Comments - Last post 39 minutes ago by duville
2,537 Comments - Last post 1 hour ago by MeguminShiro
236 Comments - Last post 1 hour ago by MrShobijin
1,403 Comments - Last post 2 hours ago by cpassuel
25 Comments - Last post 2 hours ago by OneManArmyStar
16,777 Comments - Last post 3 hours ago by Zolivv
33 Comments - Last post 2 minutes ago by Schnapser29
16 Comments - Last post 5 minutes ago by hawkeye116477
75 Comments - Last post 7 minutes ago by DogOnSG
10,028 Comments - Last post 10 minutes ago by Fluffster
56 Comments - Last post 18 minutes ago by ChocolateVC
261 Comments - Last post 18 minutes ago by davidpfarrell
63 Comments - Last post 26 minutes ago by Vampus
So, a mate of mine starts rambling about this project idea of his — keeping it vague for now 'cause he's gonna try and market it or something — but basically it’s gonna involve AI, voice, the works. Since I’ve been off work recovering from some delightful dental surgery (10/10 don’t recommend), he asked if I could whip up a basic offline AI to help with his prototype.
One week later, in between games and wrangling the kids, I’ve somehow ended up knee-deep in a full-on desktop AI assistant. I’m calling it Version 0.8 for now, with my “MVP” version being 1.0.
Right now it uses FFmpeg, Whisper, LLaMA3, and Coqui TTS. It handles both text and voice input/output, caches WAVs, convos, user settings, and has a few colour themes 'cause who doesn’t love a bit of flair. Currently working on per-conversation caching and trying to make convos reference each other — which is as fun as it sounds.
Also, the AI voice? Sounds like a half-baked call centre operator. Absolutely cooked. I’m adding more voice options soon so it stops sounding like a robo-Karen trying to upsell me internet plans.
Performance-wise, I’ve managed to take voice response from "go make a cuppa" times down to about 6–8 seconds, thanks to streaming chunked WAVs and throwing the GPU at it. Still not lightning, but hey, it’s no longer yelling into the void and waiting for enlightenment.
Anyway, point is — since I was putting together a train anyway, thought I’d ask: anyone got feature ideas? Already blown past what my mate expected, so I’ve got a pretty hefty roadmap going. But I’m all ears for wild suggestions, practical or ridiculous.
Here is your entry to a progressive train. Good Luck and Enjoy ^^
Just finalised the addition of allowing the creation of different conversations, user defined conversation titles, conversational tabbing, persistent / cached conversations and deleting conversations ^^ Currently the entire App is 755 Megabytes. Let's watch that expand >.<
Comment has been collapsed.