Easy Offline Text-to-Speech on Raspberry Pi: A TTS Guide

Transform your Raspberry Pi into an offline TTS system with simple, ready-to-use code.

BeginnerFull instructions provided1 hour2,164

Things used in this project

Hardware components

SaraKIT

Raspberry Pi Compute Module 4

Raspberry Pi 4 Model B

Story

Unveiling the Power of Offline TTS with Raspberry Pi and SaraKIT

As of 2024, we've scoured the internet to bring you what appears to be the best Text-to-Speech (TTS) solution for Raspberry Pi. If you find something even better, we're all ears!

Our chosen TTS solution takes advantage of the SaraKIT, which is not only equipped with a stereo amplifier but also boasts three microphones and a specialized audio processor. This setup cleans up voice audio and supports speech recognition from distances up to 16.4 feet, enabling the development of sophisticated projects that we detail on our website.

While TTS doesn't require SaraKIT—you could even use simple headphones or a basic speaker—the full setup shines when used to create voice assistants, speaking devices, or integrated home automation systems. While online services like ElevenLabs offer top-quality voice synthesis for a fee, and Google Text to Speech provides accessible voice services, our focus here is on robust offline processing.

After a thorough search for the best, fast, and easy-to-install offline TTS solution, Piper stands out as the premier choice. Piper is fast, delivers high-quality voice output in real-time, and is optimized for Raspberry Pi 4. To make the installation process as straightforward as possible, we've simplified it further for you. You can find a demonstration and detailed guide below.

Test Piper's capabilities at the following link:

https://rhasspy.github.io/piper-samples

This setup enhances the Raspberry Pi’s audio handling capabilities and is ideal for anyone looking to implement advanced voice interactions without relying on internet connectivity. Our project not only showcases how to set up Piper but also invites the community to improve and expand upon it. If you have your own code enhancements or alternative solutions in C++ or Python, please share them, and we might feature your contribution in our repository.

Piper on GitHub:https://github.com/rhasspy/piperhttps://github.com/rhasspy/piper-phonemize (an additional component)

Voices for Piper:https://huggingface.co/rhasspy/piper-voices/tree/main

Installation on SaraKIT

Assuming the basic SaraKIT drivers are already installed https://sarakit.saraai.com/getting-started/software, follow these steps to install Piper:

sudo apt-get install libasound2-dev
sudo apt-get install libfmt-dev
sudo apt-get install libspdlog-dev
git clone https://github.com/SaraEye/SaraKIT-Text-To-Speech-Piper-Raspberry-Pi piper
cd piper

sudo cp -r lib/piper/lib/*.* /usr/local/lib/
sudo ldconfig

make

To use a language other than English, download the required language model from https://huggingface.co/rhasspy/piper-voices/tree/main and place it in a directory, e.g., `lib/piper/models`.

Start speech recognition by running:

./ttsDemo

Below is the text to speech script in your chosen language, available at:https://github.com/SaraEye/SaraKIT-Text-To-Speech-Piper-Raspberry-Pi:

#include <functional>
#include <iostream>
#include <string>
#include <signal.h>

#include "lib/piper/piperclass.hpp"

using namespace std;

int main() {
	//Choose your language and voice
	piper::PiperClass piper("lib/piper/models/en/amy/en_US-amy-medium.onnx", "lib/piper/lib/espeak-ng-data");
	
    while (true) {
        string text;
        cout << "Enter the text to synthesize (CTRL+C to finish): ";
        getline(cin, text);

        piper.say(text);
    }

    return EXIT_SUCCESS;
}