Leon VS Speech-Recognition

It's indeed suspicious. You're sending your voice samples, your various services accounts, your location and more private data to some proprietary black box in some public cloud. Sorry, but this is a privacy nightmare. It should be open source and self-hosted like Mycroft (https://mycroft.ai) or Leon (https://getleon.ai) to be trustworthy.

I literally had this thought a couple of days ago and went down a small rabbit hole looking into it too! There's some stuff out there (I saw Mycroft and Coqui mentioned in the comments already, also check out Leon, Jarvis, and OA although not sure they all deploy to Linux) but ultimately, I just don't think the tech is there yet.

Mycroft is pretty decent and there are a few other similar open source projects if you're interested (https://github.com/MycroftAI, https://github.com/leon-ai/leon)

Take a look at Leon I'm not sure it's what you're looking for but it look pretty awesome.

Leon is an open-source personal assistant who can live on your server. He does stuff when you ask him to. You can talk to him and he can talk to you. You can also text him and he can also text you. If you want to, Leon can communicate with you by being offline to protect your privacy.

git clone https://github.com/leon-ai/leon.git

There is also Leon - https://getleon.ai. But I’m not using any of the self hosted yet.

A platform that allows for customization provides the option to build on or extend existing features, allowing you to create a more functional product and a more pleasant experience for your clients or patients. Spurwing is a leading provider of Time Management Solutions thanks to our Appointment Scheduling API and rockstar support team.

For example, an appointment scheduling service like Spurwing uses two-way syncing with external calendars. Two-way syncing ensures that no matter what calendar a provider uses, they see an up-to-date schedule of appointments.

GitHub: https://github.com/Spurwing/Speech-Recognition This is our simple yet powerful server-client implementation with Speech Recognition in the browser. It works on any device that uses a modern up-to-date web browser (FireFox or Chrome recommended).