Showing 1-20 of 87 projects
Text-to-audio model for generating realistic speech and sounds
Creative coding library for web art and design
An ultra-realistic text-to-speech model for generating natural-sounding dialogue and audio.
Open-source speech toolkit with state-of-the-art ASR, TTS, translation, and audio processing capabilities.
Sonic Pi is a live coding environment for creating music and sound using Ruby.
AudioGPT is a powerful tool for understanding and generating speech, music, sound, and talking heads using AI.
A collection of various audio effects plugins for PipeWire, a sound server for Linux.
A sound cloning tool that lets you use your voice or any sound to record audio, with a web interface.
A tiny data-over-sound library for IoT, pairing, and serverless applications.
NewsBlur is a personal news reader that allows users to discover, discuss, and share news content.
An open-source audio programming environment for sound synthesis and algorithmic composition.
Orpheus-TTS is a high-quality, real-time text-to-speech library for creating human-sounding AI voices.
HTML5 JavaScript recording library that supports multiple audio formats and provides features like ASR and DTMF.
A TypeScript library for visualization and creative-coding, enabling developers to create dynamic, interactive graphics and data visualizations.
A Soundcloud client built with React and Redux, focused on music discovery and playback.
An VSCode extension that gives you fun audio compliments while you code, based on the keywords in your code.
Two conversational AI agents that switch from English to a sound-level protocol after confirming they are both AI
BespokeSynth is a C++ software modular synth for music production and sound design.
A JavaScript library for creating MIDI-based web applications with support for synesthesia effects and sound conversion.
A powerful audio and music analysis library for developers working with audio-related applications.
Get weekly updates on trending AI coding tools and projects.