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.

Video transcription service built as a part of Practice School - I course at William O'Neil, Bangalore

Voice-Controlled Music Player is a Python-based application that lets you control music entirely through voice commands. It supports both Spotify and local music playback (MP3, WAV, OGG), with commands for play/pause, skip, previous, and precise volume control.

A voice-controlled Bleach experience — speak a Bankai's name and watch it activate on screen with a particle-explosion reveal, complete with its wielder's info and pattern-based visuals.

This is backend project for FluentAI - Speech Assessment Chatbot.

This is an AI assistant which takes speech as input and performs various tasks

A simple Python application that converts audio recordings into text using the SpeechRecognition library and Google Speech Recognition API. Developed as part of my Artificial Intelligence Internship at Codec Technologies.

A Flask Webapp created as a part of "Ode-To-Code" Hackathon. Won 2nd place.

Voice-controlled CSV review updater built with Streamlit

Simple speech-to-text tool supporting file upload and live mic recording. Powered by SpeechRecognition + Gradio. Supports 13 languages.