Raspberry Pi Text-to-Speech w/ Windows 10 SpeechSynthesizer

We absolutely love when developers harness the real-time capabilities of the PubNub API and extend it to the Internet of Things. With the affordability, capabilities, and flexibility of new embedded boards, the sky’s the limit for IoT hobbyists and developers for any skill level. So when a great project comes along, we want our readers to know about it.

Today’s featured project is from Krishnaraj Varma, who built a text-to-speech application using Raspberry Pi and Windows 10 audio output (part of the Windows 10 IoT release earlier this year).  The application enables a user to type in text, sends the command to a Raspberry Pi 2 Model B, then uses SpeechSynthesizer to speak the text.

Even better, Varma expanded his demo by integrating PubNub to allow remote users to us the application. Streaming the text over the PubNub Data Stream Network, users can send commands in real time from remote locations. Using the PubNub JavaScript SDK, the application keeps an open socket connection and listens for incoming PubNub messages on a channel.

You can see Varma’s full code repository here, including a schematic and all the code you need to build it yourself.

See it in action below: