With the brand new lightweight KittenTTS text-to-speech (TTS) model, it's possible to synthesize text into speech on lower end CPU only hardware like the Raspberry Pi 5. This means you can add some decent sounding English speech to your project without having to deal with network connections, API keys, pay-per-use pricing models, or relying on cloud providers using power hungry GPUs.

This project illustrates how to get started with KittenTTS by making a basic app to read aloud weather forecasts which are pulled from the US National Weather Service API. Once you learn the basics, you can apply them to add speech output to whatever great project you've got in the works.

We've tested KittenTTS successfully on the Raspberry Pi 4 and Pi 5. As expected, the Pi 5 is able to generate audio faster than the Pi 4.

Parts

Aside from the Pi 4 or 5, this project uses the Adafruit Voice Bonnet, and either 3.5mm powered speakers, or small JST connector speakers.