Browse applications built on music and audio technology. Explore PoC and MVP applications created by our community and discover innovative use cases for music and audio technology.
Advanced AI Assistant and MusicGen Guide for peak creativity and efficiency in radio and music production
PsychGen, developed at the AutoGen Hackathon, merges Conversational AI with personalized psychotherapy, addressing mental health issues. Utilizing robust tech like AutoGen and OpenAI, it transitions from text to audio to video for a guided psychotherapy.
TerraAI handles music files like a real musician. TerraAI is your assistant to better and automize your music making workflow.
🌟PolyGPT : Pluripotent AGI-style agent of agents that can build and deploy its own stack, go online and produce multi file multi folder multi media outputs using any tool and pipeline !
Audio pipeline for generating music via a chat interface using openai. With more time and prompting you can get the chat model the generate the art based on the chat model's prompts to generatively create art and musicfor D&D style games
We made a cool thing! It's an AI tool that turns words into music using fancy technology. This special tool changes writing into beautiful music with the help of Meta's Audiocraft.
QuakeAI is an Audiobook Generator (made for the Llama2 Hackathon hosted by Lablab.ai) that enables Authors, Writers, and live Streamers/Broadcasters to generate Spoken stories with AI generated background music that brings life to it.
We are using images, live webcam feed and user prompts, AI prompts for generating music according to the prompts
Lofi Focus is a chrome extension that automatically generates lo-fi music when browsing articles, blogs, and other sites. The ambient, chilled-out sounds create an enjoyable atmosphere to help users focus while reading.
In this hackathon, we embarked on an innovative project intersecting the realms of raga music and AI-driven audio generation. Initially, we delved deep into the intricacies of raga music and the features of advanced tools like Audiocraft and MusicGEN.
An Audiobook Generator that enables Authors, Writers and live Streamers/Broadcasters to generate Spoken stories with AI generated background music that brings life to it.
TrueCast: An AI-powered tool that monitors podcast conversations in real-time, instantly verifying claims against multiple sources and providing relevant media upon request, ensuring podcast accuracy and authenticity.
InnovAItio is a chat app that allows you to save voices into contacts and hear text messages in the sender's voice.
Easy AI Voice: A user-friendly platform empowering individuals and businesses to use customized AI voice models with ease.
This is my first hackathon project, based on the ElevenLabs tutorial.
Classic Literature Re-Imagined and Read by Artificial Intelligence
Introducing CollabTalk.ai – your ultimate tool for effortless podcast creation! Harness the power of Eleven labs AI to create content from any source and turn it into captivating audio episodes.
Accessible, platform-agnostic voice interface using advanced AI tech like ChatGPT and Whisper. Enabling personalized digital character creation, aiming to transform Human Computer Interaction and promoting inclusive communication.
Elevate your entertainment with personalized dubbed versions of foreign-language movies & TV shows. Enjoy character voices in your chosen language for an immersive and delightful viewing experience. Accessible, enjoyable, and language barrier-free! 🎬
Project Gutenborg uses AI text-to-speech models to turn Project Gutenberg's text files into captivating audiobooks. Choose from various voices to personalize your audiobook experience, and unlock the world of classic literature in a whole new way.
Yourpodcast.xyz is a tool for people to generate the podcast that they want to listen to.
Convert any research paper into a fun dialogue between two voices of your choice in the form of a podcast
Vocaly - Your Voice, Your Way! Transform, Filter, and Express Yourself with Confidence. Experience the power of our app to customize your speech, turning your voice into a unique and seamless expression of your thoughts and emotions.
A podcast generator using GPT-3.5 and ElevenLabs. Written in PromptSpace Language (PSL), Streamlit for GenAI apps. Hosted on PromptSpace, a serverless platform for PSL apps. Functionality inspired by Wondercraft.
Debate.lol is an app where you can debate the best speakers in the world on any topic of your choosing, powered by AI.
Customized voice for audiobooks for everyone to use. This could be an evolution for publishers and end-users to get their imagination of a book sounds like to come true.
"The Voich" is a cutting-edge technology aiming at making book-reading and story telling easier . Now , you can hear a book while you work , play or just relax on your couch.
A fully autonomous AI-generated toolkit for playing, running, and generating a game. What kind of game? Any kind of game you want.
Audio-Visual Novel enables creators to add engaging, natural voices to their visual novel, interactive fiction or game project seamlessly and without effort.
A speech to speech conversation. This tool converts speeches (video or audio) from any foreign language to your local language or any language of your choice.
Podbait is your engaging All in one podcast plattform. We create your Podcast with
fAIble bud is an Alexa Skill that allows you to create unique custom fable on demand for the little ones. You specify what moral or lesson be learnt and the skill will generate a unique fable for you in familiar and unfamiliar voices!
The VocalVerse is a place where you can talk with all your favorite people and characters through custom LLMs and voice models.
Introducing TalkToMe: a groundbreaking web app that transforms passive content consumption into interactive experiences. Upload podcasts, books, or docs, and our app creates a dynamic ChatSession. Ask questions, get concise answers, summaries, and more.
it can be any document and any photo for the avatar ... I chose my resume and a nice lady I made with stable diffusion running on vultr.com computers running stable diffusion web ui with docker connected to the internet with a raw ip:)
BEG Digest utilizes AI models in GCP to transcribe voice to text, then generate concise summaries. Perfect for digesting lectures or podcasts. Learn more faster.
How would a physical interface to Stabel Diffusion feel like? Let's explore that idea using MIDI controllers!
The audio-to-image conversion system classifies audio input using pre-trained models, generates a prompt, and sends it to an AI API for image creation. It has use cases in art, design, security, healthcare, education, music production, automotive, and VR.
Generate a rap song for any YouTube video by inputting the link, instrumentals, and rap style.
Creating Infinite Possibility Voice-Commanded Text-Based Adventures using Whisper and ChatGPT
Hyperbot 🤖 assists with coding queries, generates art, provides real-time updates on current affairs and weather forecasts, composes tweets, LinkedIn posts, emails, and plays music of your choice or displays your favorite YouTube video.