QuickDigest AI facilitates seamless interaction with various data formats, real-time web search, and creative image generation for advertising

DiscordNPC lets you interact with ChatGPT through a Discord voice channel, enabling a natural conversation.

PACE (Podcast AI for Chapters and Episodes) is a semantic search engine that helps you find the information you need, inter- and intra-podcasts (Project for the AssemblyAI Winter 2022 Hackathon).

Retrieval Augmented Generation (RAG) on audio data with LangChain

Using voice to keep a journal.

TagGPT: A simple ChatGPT based multimodal dialog generation engine that can "see/draw" and "hear/speak"

Transform podcast listening with our Podcast Summarizer Project! This innovative tool transcribes audio, extracts key content, and provides user-friendly summaries. The project utilizes AssemblyAI and Listen Notes APIs for transcription and episode details. Simply input an episode ID, click "Download Episode Summary," and experience podcast content

A basic web-app for image classification using Streamlit and TensorFlow.

Python-based system designed to transcribe audio files, split the transcripts into manageable chunks, create text embeddings using HuggingFace models, and employ advanced question-answering models for retrieval-based QA.

A webapp project for lablab.ai hackathon

Lumina 🧠🎓 | Turn educational video lectures into engaging MCQ based quizzes and automatic assessment. Learning has never been this fun!

Imagine an application that autonomously take down notes for you during meetings, lectures, and conversations. Check this out...

Python Speech-To-Text projects using AssemblyAI API

RealTimeTranscriber is an application that leverages the AssemblyAI platform to perform real-time transcription of audio input.

VirtuAI Helper is a Python AI program that executes scripts based on user input, converses using OpenAI’s GPT-3, controls multimedia, navigates websites, and accepts text/voice inputs. It integrates VoiceVox Engine, a Japanese text-to-speech software with over 60 text-to-speech models you can choose.

Transcribes audio WAV files or audio input from your microphone using AssemblyAI's transcription API. It prints the transcription in the terminal and saves it in a text file.

Takes audio of poetry, visually imagines it in a video.

Full-stack chatbot app that guides users through curated rabbit holes of information.

A cutting-edge project leveraging DALL-E 3 and gpt-4o for AI-driven video generation, with FFmpeg for multimedia manipulation.

A command-line application that utilizes the free version of the Assembly AI API. It transcribes any audio files into texts with 4 types of transcribing methods that user can choose.