Media tools

Dictate or transcribe audio with browser recognition, on-device AI or cloud models.

Create an original music track from a focused text prompt. Choose a duration, preview the WAV/MP3 result, and download it.

Join, trim, reorder, and blend audio tracks privately in your browser, then export one WAV or MP3 file.

Create polished videos from text prompts. Choose from the available models, durations, resolutions, and aspect ratios.

Transform a source video with an AI model that supports video guidance.

Upscale videos 2× locally, using AI and WebGPU when available with a browser fallback.

Reduce video dimensions, frame rate, and bitrate locally and export a bounded WebM file.

Combine videos and photos with direct crop positioning, customizable borders, and picture-in-picture layouts.

Add and adjust a humanoid skeleton locally in your browser or use cloud AI for provider-assisted automatic rigging.

Turn one object image into a textured 3D model. Preview the result interactively and download it as GLB.

Open 3D models locally, inspect geometry, materials and textures, then download the original files.

Preview and export rigged 3D characters with free real-time procedural animations directly in your browser.