Arby Audio delivers cinematic-grade 3D sound experiences with immersive 7.1.4 spatial audio and advanced technology. Enjoy living sound that adapts, bounces, and reacts in real time, bringing games, movies, and music to life with lifelike reflections, precise positioning, and stunning binaural effects.

🗣️ Align audio with text seamlessly on macOS, generating accurate timestamps and subtitles in multiple formats for better accessibility.

Sanskrit 梵语（读音、天城体、转写）学习

Protect beats by stamping them with a repeating audio tag.

Бот для Telegram, который распознаёт голосовые сообщения и возвращает их в виде текста

Utility to rename mp3 files based on speech content

Telegram bot: voice-to-text + OpenAI chat replies + image generation + TTS.

Python application to split up an audio file and name the parts

Discord bot that turns youtube music into a slowed or reverb version

Secure, automated practice tools for musicians — inspired by Vivaldi’s Four Seasons and engineered with AppSec principles. Blending music and security, SecureMaestro offers sandboxed tools for looping, tempo-mapping, and safe performance analysis.

Application for everyday utilities

An innovative web application that bridges the world of emotions and Carnatic music! This project analyzes your mood through text input and generates personalized Carnatic music compositions to harmonize and uplift your spirits.

This AI medical assistant listens, sees, and speaks. It uses speech-to-text, vision analysis, and text-to-speech to simulate a doctor-patient consultation.

Scriptoria-Project is an AI-powered framework designed for intelligent document parsing, structured data extraction, and dynamic annotation. Built with modularity and performance in mind, it empowers seamless integration with NLP pipelines, making it ideal for research and production environments.

A multimodal framework that analyzes both audio & facial imagery to detect emotional states via Valence, Arousal & Dominance (VAD) scores, & recommends music aligned with the user’s emotional context. The system bypasses transcription by extracting VAD signals directly from raw inputs & uses emotion-music mappings for personalized recommendations

Mac-friendly CLI for speech-to-text with stable-ts (stable_whisper): transcription, forced alignment, SRT/VTT/TXT, CJK-aware wrapping, MPS acceleration.

PronouncePerfect helps kids improve pronunciation and reading with interactive speech-based activities.

A Streamlit web app for AI-powered voice cloning using Coqui XTTS v2. Record or upload reference voices, clone speech in multiple languages, and generate natural audio outputs.

Local, offline pipeline that finds clean ad-break points via scene cuts + quiet audio, transcribes nearby context with Whisper, and exports JSON/SRT/timeline for ad conditioning.

AWS Lambda function in Python to merge or zip MP3 files stored in Amazon S3, with authentication via x-api-key