Hyperframes Media

Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing background from video/images, choosing TTS voices or whisper models, or chaining TTS -> transcribe -> captions. Each command downloads its own model on first run.

cosmicstack-labs Updated 491 repo stars
Mercury Skills

File contents

cosmicstack-labs/mercury-agent-skills commit 117573d936

Frequently asked questions

npx get-skill add cosmicstack-labs/hyperframes-media