A wrapper for the Google Text To Speech API with various features.

多言語で会話するLINE上のAIボット Conversation BOT in LINE speaks multilingual.

API to convert pdf files to audiofiles

This GitHub repository contains a webpage/handout that offers text-to-speech and text accessibility features, designed with inspiration from Edward Tufte, along with a good dark theme.

AI video dubbing using Google APIs automates translation and dubbing by transcribing audio with Speech-to-Text, translating it with the Translation API, and generating speech with Text-to-Speech. Cloud-based processing ensures scalable, efficient dubbing, making videos accessible to global audiences in multiple languages.

This repository is the backend part of our ICT Project made for Häme University of Applied Sciences and Cinia Oy. The project goal was to create a proof of concept - how could speech recognition be utilized in emergency call processes.

Small Framework for linking different AI models to create a Voice-To-Voice interface.

Hackathon Project: an accessibility app for individuals with severe visual impairment using APIs to identify everyday objects & text and read pdfs aloud, as well as to help the individuals' educational learning. Created for StormHacks 2022.

Enter the interactive realm of our dazzling app! Speak your text into life with a symphony of diverse voices, each with its own rhythm, pitch, and tone. Immerse yourself in a world where your words dance to a unique beat!