Porcupine   VS Leon

I call it DaVinci. DaVinci uses Picovoice (https://picovoice.ai/) solutions for wake word and voice activity detection and for converting speech to text, Amazon Polly to convert its responses into a natural sounding voice, and OpenAI’s GPT 3.5 to do the heavy lifting. It’s all contained in about 300 lines of Python code.

Download pre-trained models: "Porcupine" from Porcupine Wake Word and Video Player Context from Rhino Speech-to-Intent repositories - You can also train a custom models on Picovoice Console.

Below are some useful resources: Open-source code Picovoice Platform SDK Picovoice website

Download the Porcupine model and turn the binary model into a base64 string.

Download Porcupine (i.e. Deep Neural Network). Run the following to turn the binary model into a base64 string, from the project folder.

Porcupine SDK Porcupine SDK is on GitHub. Find libraries for supported MCUs on the Porcupine GitHub repository. Arduino libraries are available via a specialized package manager offered by Arduino.

Looking for more? Explore other languages on the Picovoice Console and check out for fully-working demos with Porcupine on GitHub.

Don't forget to visit Porcupine's Wake Word's Github repository to see Python demos. If you want to do something similar to the video above, find the open-source codes here

I sometimes see the term "end-to-end", and it always passes right by my ears as marketing jargon. For example, there was a recent post today that linked to this page: https://picovoice.ai/, and you'll find the statement "... end-to-end platform for adding voice to anything on your terms". I did a quick Google search and it seems like the term is used in many different contexts (e.g., encryption, enterprise software for product development, etc.), but to be honest, I'm just not getting it. Maybe someone can explain here within the realm of embedded software? Could you provide some examples as well?

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.