Digital Samba Skills

Generates background music, vocal tracks, covers and stems for videos with the open-source ACE-Step 1.5 music model.

Generates voiceovers, sound effects and music for videos with the ElevenLabs APIs, including voice cloning.

Converts, resizes, compresses and trims video and audio with FFmpeg, and prepares media files for use in Remotion projects.

Generates short video clips from text or images with the LTX-2.3 model on Modal, for b-roll, animated backgrounds and motion content.

Composes video in Python with MoviePy 2.x, such as adding accurate text, labels and lower thirds over AI-generated clips or building short ad spots.

Records browser interactions as video with Playwright, for demo footage, app walkthroughs and UI flows used in Remotion videos.

Gives prompt patterns and settings for editing photos with Qwen-Image-Edit on RunPod while preserving the person's identity.

Covers the toolkit's own Remotion components, custom scene transitions and project conventions for building videos in React.

Sets up and manages RunPod serverless GPU endpoints for the toolkit's image editing, upscaling, watermark removal, talking-head and speech tools.

Creates explainer videos from a text brief with open-source AI models on cloud GPUs for voiceover, images, music and talking heads, rendered with Remotion.