porcupine

> also, "GPT-4o continuously listens to speech through the audio stream," is going to be problematic This seems like a good place to leverage a wake word library, perhaps openWakeWord or porcupine. Then the user could wake the device before sending the prompt off to an endpoint. It could even have a resting or snoozing animation, then have it perk up when the wake word triggers. Eerie to view, I'm sure... https://github.com/dscripka/openWakeWord https://github.com/Picovoice/porcupine

Precise [1], Snowboy [2], and Porcupine [3] are all designed to work offline. [1] https://github.com/MycroftAI/mycroft-precise [2] https://github.com/kitt-ai/snowboy [3] https://github.com/Picovoice/porcupine

Link to the github repo: https://github.com/picovoice/porcupine The keyword generating application: https://github.com/Picovoice/Porcupine/tree/master/tools/opt... The keyword generating application is free for personal use only and requires a license for commercial use, but there's no pricing available and it only provides an email address for contacting about purchasing a license. If anyone from the team is reading this, the information above should be front and center on the landing page. I would guess that 99% of your site visitors are going to bounce on your landing page because the relevant information is buried so deeply.

> Picovoice is a team of applied scientists and engineers who strive to build a future where our lives are enhanced with ambient voice AIs, while respecting your privacy. Oh wow, thank you! I also saw a reference that this is all open-source but https://github.com/Picovoice/ does not have a Picovoice repository. Is it https://github.com/Picovoice/Porcupine?

That's odd. If there are errors in the console. Please open an issue in the GitHub repo is possible: https://github.com/Picovoice/Porcupine Otherwise, I am thinking it could be something related to the microphone?

thanks a lot for the feedback :) Take a look at this standalone demo if you like https://github.com/Picovoice/Porcupine/tree/master/demo/js it should be a matter of tweaking a few parameters.

Looks like this is source for the wake word engine: https://github.com/Picovoice/Porcupine But their site says to email for licensing, which bodes poorly. EDIT: License for "Porcupine" is Apache but with this: THIS LICENSE APPLIES TO ASSETS IN THIS REPOSITORY INCLUDING DOCUMENTATION, SOURCE CODE, BINARIES, AND RESOURCE FILES EXCEPT FOR THE OPTIMIZER TOOL, ITS ASSOCIATED RESOURCE FILES, AND KEYWORD FILES GENERATED USING IT COLLECTIVELY LOCATED UNDER Porcupine/tools/optimizer. THE OPTIMIZER TOOL AND KEYWORDS FILES GENERATED USING IT ARE NOT GOVERNED BY THIS LICENSE. SPECIFICALLY THEIR USE IN COMMERCIAL PRODUCTS WITHOUT ACQUIRING A LICENSING AGREEMENT FROM PICOVOICE IS STRICTLY PROHIBITED.

Thanks for the question. You can use our first product: https://github.com/Picovoice/Porcupine. It is a voice-control (wake-word) engine. It allows you to detect multiple keywords (phrases) in the audio stream in real time with no delay and it fully runs on-device. No cloud connection required.