Project Link Proposal/Voice browser

Proposal Overview

• Like a web browser, but with speech-to-text input and text-to-speech output.
• It recognizes several wake words, and based on that sends the query that comes after the wake word (in the form of a sound clip) to one of the online voice APIs (OK Google, Cordana, Siri, Alexa, etc.). The answer comes back as a sound clip and is played over the speaker.

Technical documentation

• We would have to see how to do the wake word recognition, and which online voice APIs would be accessible with a device like this.

Presentations

• https://github.com/connected-devices/ideas/issues/1
• https://discourse.mozilla-community.org/t/rfc-picking-the-living-room-microphone-as-our-only-focus/8780