“Audio and video”

Attaches an audio track to a video file.

Generates lip-synced or audio-reactive video from an image and an audio track.

Pulls the audio track out of a video file and saves it as a separate audio file.

Converts images, audio, video and documents locally in the browser using WebAssembly.

WebAssembly build of whisper.cpp that transcribes microphone or file audio inside the browser.

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

Transcribes audio or video with faster-whisper and can translate the result, with subtitle export.

Converts files between many audio, video, image and document formats.

Generates a video with a soundtrack from image, audio and video references using MiniMax-H3.

Clones a voice from a short audio sample and speaks new text in it, using the F5-TTS and E2-TTS models (unofficial demo).

Fast Whisper transcription for audio or video files, with subtitle output and a translate option.

Piano-roll MIDI editor in the browser.

Records the screen into a GIF in the browser, with frame trimming before export.

Transcribes or translates speech from an audio file, URL or microphone with Whisper running inside the browser tab.

Sketch chiptune melodies in a pattern editor and share them by URL.

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

Generates subtitle files from a video or audio file using Whisper.

Syncs a speaker's lip movements in a video to a new audio track using latent diffusion.

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

Converts an ebook into an audiobook, with support for more than 1,100 languages.

Turns an image into a video using a text prompt, with the Wan2.2 14B model.

Online player for MIDI and video game music files with SoundFont support and a large song catalog.

Web-based collaborative editor for live coding sounds and images with several engines.

Turns a text prompt into a short video with audio in four steps, using the MiniMax-H3 FlashGen LoRA.