Very cool, I've daydreamed about building something similar but always convinced myself I'd have to wait until text-to-speech was better to really incorporate all the sources I'd like. Awesome work!
Long term I'm going to go with something self-hosted using Tortoise TTS etc but I also want to break away from Google's Cloud Speech as that can cost me hundreds a month when the user base has a peak so this looks great, thank you!