As Snowden told us, video and audio recording capabilities of your devices are NSA spying vectors. OSS/Linux is a safeguard against such capabilities. The massive datacenter investments in US will be used to classify us all into a patriotic (for Israel)/Oligarchist social credit score, and every mega tech company can increase profits through NSA cooperation, and are legally obligated to cooperate with all government orders.
Speech to text and speech automation are useful tech, though always listening state sponsored terrorists is a non-NSA targeted path for sweeping future social credit classifications of your past life.
Some small LLMs that can be used for speech to text: https://modal.com/blog/open-source-stt
Just a page with the name of the project when I checked just now. Nothing else.
Look. Is part of the plan to build and distro an OTA flash for my ~9 echo flex models deployed out on the world? They have everything they need for interaction, as well as networking and Bluetooth beaconing.
Check your shit then bc it’s a long page with docker containers and venv distributions, blog, about, sources, etc.
That said I don’t know this project. I do know home assistant though. If you want voice control at home that is secure use that. You can use their hardware or different hardware. The important thing is voice commands can be processed entirely locally, eg without internet access.
My iot setup, including voice commands, is restricted to a physical switch that has no internet access and itself is on an isolated vlan. I can view cameras remotely by forwarding the service through headscale, which is only turned on when necessary. It’s not a perfect system, nothing is, but it’s essentially airgapped when I am home and I do not have to worry about “cloud servers” with rogue employees that look at unencrypted data (which is sold as encrypted but often only encrypted in transit but unencrypted at rest so they can sell you out to the cops) or lazy cybersecurity staff that leave gaping holes in their massive targets for ransomware attacks or whatever
seems more mature, and external automation oriented. I’m interested in developing voice text editing tools. Don’t really know if what I linked is best suited platform.
This is a good point. Home assistant is not going to work for your application
The website seems to work fine for me, but they seem to only support open hardware (e.g. Raspberry Pi or Mycroft). That doesn’t mean it wouldn’t work on other things though, especially with open software, but I wouldn’t be surprised if Echos require updates to be signed by Amazon, so it might require some hacking.
I googled the echo flex and I don’t see any evidence someone has gotten the bootloader unlocked or have been able to install a custom ROM/OS. Depending on the generation the flex is based on, it could be Linux or android based. Have you been able to access the os on your devices? If not, you might have a lot of work on your hands to get enough access to install any kind of non-stock OS.