It's a library for C / Micropython / AtomVM, so you could send the result over a lora radio, ESPNOW, WAN, match it in a switch statement to activate a relay, draw on the LCD.. that's up to you.
Many ESP32S3 dev boards have a microphone and speaker header available conveniently on the board, so I have been using that to respond via Babytalk's text to speech capability.
I'll improve the README to make it a little more clear.
Thank you for the explaination. So it is a library and would require someone to adjust it to their use case. That's what got me confused: wide open use case, but nothing tangible. I mean, if an ESP device is doing STT+TTS, then what am I supposed to be talking to? But if it is an ESP device that can do ANY->TTS and/or STT->ANY with some code customization needed, then I think I get it.
I wrote the README from the perspective of being understandable by the lay person, and I think I left out some vital clues about this being a software building block for making your own ESP32 projects more intelligent. I pushed a README update to make it 0.1% more clear.
As for what to talk to.. or the ultimate purpose lol.. you could do simple device control scenarios ("lights off"), do hands-free sensor readings ("temperature at 95 degrees"), change wifi settings via voice ("switch access points"), etc.
I use it to control an agent-powered diverse device sensor network in my home and my truck. Much of the capability needs Internet access, but having on-device speech to text and text to speech means I can still do some stuff when I didn't bring the Starlink with me. On-device STT opens up a lot of low bandwidth (lora) opportunities too.
Thanks. I will ask an LLM to investigate if this could be implemented in a STT-to-HID standalone offline device. If I reach any semblance of success, I will let you know so the projects can link to each other.
It seems like everyone is more worried about how something was made rather than what it is or whether or not the work is good on its own merit. Ironic from a group that is surely using AI tools in their own work.
If your application is pricing sensitive, check out DeepInfra.com - they have a variety of models in the pennies-per-mil range. Not quite as fast as Mercury, Groq or Samba Nova though.
(I have no affiliation with this company aside from being a happy customer the last few years)
DeepInfra is amazing in terms of price, like really, they have the Qwen3 embedding model for $0.002 per mn tokens. That's an order of magnitude cheaper than most alternatives with better benchmark scores. But the performance P99 is slow and the variance is huge. For latency sensitive workloads it's problematic, if they can fix that it'll be a no-brainer to use them. DeepInfra does tend to have the lowest prices of any API provider.
Sounds great to me! Just be sure the AI is capable of taking on various personas because not everyone you meet is a believer in nonviolent communication.
A tip, Miami guy to Miami guy - the best devs eschew PHP like the plague. The remaining PHPers are desperate work-a-day sorts who will not be bringing the latest hotness to your project. Hire an Elixir or Haskell expert and you're gonna get a much more well-traveled coder.
Kudos on your bold undertaking! I've been a side-lined QNX admirer for some time, though not a potential user in most cases. A good next step would be a series of blog posts where the author takes on common types of enthusiast projects and unpacks how QNX's strengths can be applied in those scenarios.
