Multimedia

Just playing around.

Open source multilingual Android application for streaming music from YouTube Music

Automatic headphone equalization

Parrot AI is the top celebrity voice generator. Create fun audio clips to roast your friends, send birthday messages, and light up your group chat!

リアルタイムボイスチェンジャー Realtime Voice Changer. Contribute to w-okada/voice-changer development by creating an account on GitHub.

Easily train a good VC model with voice data

The best app for practicing music. Remove vocals, separate instruments, master your tracks, and remix songs with the power of AI. Try it today!

Substital is a browser extension that lets you easily add subtitles to videos online.

Web application for archival and reading of manga/doujinshi. Lightweight and Docker-ready for NAS/servers. - Difegue/LANraragi

YTLitePlus - Supercharge your YouTube Experience

Create custom designs and graphics with Playground

A multi-voice TTS system trained with an emphasis on quality - neonbjb/tortoise-tts

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching" - SWivid/F5-TTS

At the forefront of innovation as an open-source ecosystem that hosts cutting-edge AI voice cloning technologies.

Photo gallery for Linux. Contribute to blissd/fotema development by creating an account on GitHub.

This new software boosts sound quality, volume, clarity and bass on your PC. FxSound will make your audio jump out of your speakers.

Beautiful.ai is the best AI-powered presentation software for teams. Stay on brand, level up and automate presentation design, and collaborate from anywhere.

HoldSpeak is a AI-powered app that allows you to type 3x faster

View and edit graphs. Contribute to SeaDve/Delineate development by creating an account on GitHub.

An extensible text-to-diagrams library that works in both browser and node.js - hikerpig/pintora

VALL-E is a neural codec language model using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as a prompt. We also extend VALL-E and train a multi-lingual conditional codec language model. VALL-E X can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker’s voice, emotion, and acoustic environment.

Capture professional quality screen videos

Make hand-drawn style wireframes quickly and easily.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Inference and training library for high-quality TTS models. - huggingface/parler-tts

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production - coqui-ai/TTS