Skip to content

Rb tts

Text-to-Speech Engine

Introduction

🔊 Introducing REBOTNIX SDK's Revolutionary "Text-to-Speech" Engine! 🕵️‍♂️📸

Elevate your content with crystal-clear synthetic speech at your fingertips. With our cutting-edge technology, you can transform any text into high-quality WAV files at a stunning 44100 Hz, ensuring a truly immersive listening experience. Everything running smoothly on your edge device.

Requirements

  • A GUSTAV from the Orin series
  • Jetpack version 5.2 or higher
  • Python3.8

Installation

#install first with script - only once
./install.sh

#load rebotnix container
source rb_container_tts/bin/activate

#run inference on console
python main.py

Code Snippet

import sys
import os

#check for ROOT_PATH variable
try:
  sys.path.append(os.environ['ROOT_PATH'])
except:
  print("Please set the variable ROOT_PATH.")
  sys.exit(0)

#import rb_tts
from libs.rb_tts import rb_tts

#initialize TTS engine with a model file
voice_creator = rb_tts("./models/rb_voice_container_John.rvt")

#set text you want to synthesize
text = "Hello, this is an artificial voice sample."

#run creation and save output to wav file
voice_creator.create(text, "./output.wav")

Output

Download

Download RB_TTS