实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

Ultimate Vocal Remover 5 with Gradio UI. Separate an audio file into various stems, using multiple models

A multimodal chat interface with many tools.

WonderWhy is a cross-platform family education AI application based on LLMs and Generative AI Technology.

This project provides a Gradio-based web application that allows users to interact with an SQLite database using natural language queries. It leverages the LangChain library and OpenAI's language model to convert plain English questions into SQL queries and execute them on the provided database.

Gradio App for Deploying a Classification Machine Learning Model for Churn Prediction

🍎 Fruits Classification App (Gradio) 🍌

Official repository of Team DeepVision, competing in the Gidy.AI Techpreneur Hackathon 2025 at Saveetha Engineering College. Led by Vikhram S, this project leverages DeepVision AI to evaluate startup viability, assess market potential, and provide data-driven insights for tech-driven entrepreneurship. 🚀 #AI #StartupEvaluation #DeepVision

PresentaPulse leverages the power of LivePortrait and Real-ESRGAN to create ultra-realistic animated portraits. Developed by Tarek Tarabichi from 2TInteractive, this tool integrates advanced AI models to enhance image quality and create stunning animations.

Analyze the sentiment of product reviews in English, Dutch, German, French, Italian, and Spanish. Focused Sentiment Analysis for eCommerce.

Violent human action recognition using drone

"DALLE-3 MASTERWARE +" is a wrapper application of OpenAI's Dall-e-3 built in Gradio to provide a GUI interface for user friendly interactions with the official OpenAI API

A tool to convert PDF files to detailed Markdown descriptions using VLMs