Free online audio and video tools

Light-weight General MIDI synthesizer and MIDI player written in WebAudio JavaScript, with a keyboard demo.

Browser music tracker driving a built-in synthesizer, for composing patterns and sharing songs.

Progressive web app with a 64-step drum sequencer for building beats.

Free text-to-speech tool with voice choices and emotion control for the spoken output.

Frontend web app for exploring piano chords freely and interactively with sound.

Electric guitar effects and cabinet emulator built with the Web Audio API.

Toolbox for musicians that routes and transforms MIDI between devices directly in the browser.

Web-based MIDI editor and synthesizer where you write and play sequences.

Programmable sequencer for chiptunes that runs in the browser.

Online tool for sketching and sharing instrumental music, an extended fork of BeepBox with more instruments.

Browser drum machine and beat sequencer with eight voices, sixteen steps and chainable patterns.

Bytebeat player with a collection of formulas from around the web, where music comes from one-line math code.

Interactive visual music theory pages with playable sound examples.

Minimalistic web app for creating electronic music with a step sequencer and synth.

Creates a short video from a still image and a text prompt using the Wan 2.2 14B model.

Chiptune-style tracker for composing retro music, with an online version.

Turns typed text into spoken audio, with optional voice description or a reference recording to clone the tone.

Generates short videos with synchronized audio using the LTX-2 Turbo model.

Generates videos with a synchronized soundtrack using the MiniMax H3 Turbo LoRA model.

Turns text into natural speech with the 82M-parameter Kokoro model and several voices.

Hosted Whisper demo that transcribes or translates microphone input and uploaded audio.

Fast video generation using the distilled LTX Video 13B model from Lightricks.

Generates speech, laughs and music-like sounds from text prompts with Suno Bark.

Clones a voice from a short reference sample and speaks given text in it.