Audio Hub

Testing hub for AI audio services including TTS, STT, STS, and video generation with voice cloning support.

February 4, 2026

Ongoing

1 views

Overview

Audio Hub is a testing platform for AI audio services including Text-to-Speech (TTS), Speech-to-Text (STT), Speech-to-Speech (STS), and video generation with voice cloning support.

Features

TTS Testing: Multiple voice models including XTTS-v2

STT Testing: Whisper-based transcription testing

Voice Cloning: Test custom voice models

Video Generation: Audio-to-video with lip sync

Technical Stack

React/TypeScript frontend with FastAPI backend. Integrates Whisper for STT and XTTS-v2 for TTS capabilities.

Related Projects

Aurora Language Center

Production-ready AI-powered language learning platform with 50+ specialized agents, hybrid LLM support, and comprehensive learning features.

Gothic Audiobooks

AI-powered audiobook generation using XTTS-v2.

CrowFlow

Enterprise-grade workflow automation platform with visual builder, AI integration, and real-time collaboration.

7 views

The Apprentice

AI Assistant

The Apprentice

Hello! I'm The Apprentice, Jorge's AI assistant. I can help you explore his portfolio, learn about his projects, or answer questions about his work in AI engineering. What would you like to know?