Speech Synthesis On Raspberry Pi with KittenTTS

Make your Raspberry Pi read a personalized weather forecast using the open source KittenTTS text-to-speech model

by Tim C

published August 12, 2025, last edited October 29, 2025

posted in Sensors/ Weather Raspberry Pi Internet of Things - IOT Programming/ Python Breakout Boards/ Amplifiers/Sound

Save Download

Intermediate

Project guide

Voice Bonnet Setup

Raspberry Pi OS Setup

First get the latest release of Raspberry Pi OS installed on your Pi and update all of the built-in software with apt. If you are comfortable with the Raspberry Pi imaging and setup process, you can follow the steps listed here under the quick start prerequisites. If you'd like more details, a more thorough guide page can be found here.

Blinka Setup

1. Install Blinka by following the automated install section on this guide page.

2. Install the proper gpio library based on whether you are using a Raspberry Pi 4, or 5.

Activate the same virtual environment created in step 1 if it is not already active.

Install Voicecard Software

This process is documented in more depth in the Voice Bonnet guide.

Make sure you've got the Voice Bonnet installed, and I2C support installed as well!

When you run

Copy Code

sudo i2cdetect -y 1

sudo i2cdetect -y 1

you should see an entry under 1A, indicating the hardware sees the audio card. The number may also appear as UU if you already installed software.

i2cdetect output showing the bonnet connected at the address 0x1a

raspi-config main menu with Interface Options selected

raspi-config Interface Options menu with I2C selected

If you don't see the 1A address, then you need to troubleshoot I2C and the bonnet connection before moving on. Ensure that I2C is enabled and that the bonnet is seated correctly on the Pi headers.

To enable I2C:

Run sudo raspi-config.
Select Interface Options and press enter.
Select I2C and press enter.
Select Yes and press enter.

If you see 1A address in the grid, then install the driver software with these steps:

Download File

Copy Code

git clone https://github.com/HinTak/seeed-voicecard
cd seeed-voicecard
git checkout v6.12
sudo ./install.sh
sudo reboot

git clone https://github.com/HinTak/seeed-voicecard
cd seeed-voicecard
git checkout v6.12
sudo ./install.sh
sudo reboot

At the end you should see something like this:

Terminal output of successful completion of the voicecard install script

Reboot the Pi to apply the settings set in the last step.

Checking for the Card

After the Pi comes back up from the reboot, check for the card by running this command.

Copy Code

aplay -l

aplay -l

Output of aplay -l command showing the voicecard as one of the connected sound devices.

Take note of what card number the device has. You may need to use the card number to output audio from the device. In the picture above, the voicecard is card number 3, yours may be a different number.

You can use alsamixer to adjust the volume, don't forget to select the card with F6 or 's' key.

alsamixer application showing the choose sound device menu with the bonnet voicecard device highlighted.

A gain of about 60% is plenty loud! The slider marked headphone on the far left controls the volume of output from the 3.5mm jack on the voice bonnet. The sliders marked speaker near the center control volume of output from the JST speaker connections.

alsamixer application volume setting page with headphone volume set to 60.

Headphone/Speaker Test

Make sure the Audio On/Off switch is set to ON!

With either headphones plugged into the headphone jack or speaker(s) attached to the JST speaker port, run

Copy Code

speaker-test -c2

speaker-test -c2

You should hear white noise coming from speakers connected to the voice bonnet 3.5mm jack or JST speaker connection(s). If you do not hear anything, then you need to direct the audio output to the correct sound card by using the -D or --device argument. This is where you need the sound card number for the voice card that you can find with aplay -l. To specify the device use plughw:#,0 as the argument value, replacing the # with your card number. For example when the voicecard is device number 3:

Copy Code