hyperframes-media

Name: hyperframes-media
Availability: InStock
Author: Bora

Preprocess HyperFrames assets with Kokoro TTS, Whisper transcription, and u2net background removal.

248|32|Updated Mar 30, 2026

Search Tags:#video #transcription #tts #voiceover #captioning #background-removal #hyperframes

Ready to run

npx skills add https://github.com/boraoztunc/skills --skill hyperframes-media-boraoztunc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hyperframes-media
Source: https://github.com/boraoztunc/skills/tree/main/hyperframes-media
Command: npx skills add https://github.com/boraoztunc/skills --skill hyperframes-media-boraoztunc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.

Core Features & Use Cases

Generate speech audio locally with Kokoro-82M. No API key.
Produce transcripts with word-level timestamps for captions.
Remove backgrounds from video or image to create transparent overlays for compositions.
Output is cached under ~/.cache/hyperframes/ for reuse across projects.

Quick Start

Generate a voiceover from text, transcribe it for captions, and remove backgrounds to create transparent overlays for your HyperFrames projects.

Frequently Asked Questions about hyperframes-media

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a voiceover from text and add captions to a video?▼

Generate TTS audio with the Kokoro model, then run the output through Whisper transcription to create word-level timestamp caption files for your video project.

Can I remove the background from a video to create a transparent overlay?▼

Remove video or image backgrounds using the u2net model to create transparent overlays for compositing in tutorials, product demos, and marketing video projects.

Do I need an API key to run local text-to-speech for video narration?▼

No API key is required. Speech audio is generated locally using the Kokoro-82M text-to-speech model, which downloads automatically to your cache on the first run.

What is the best way to chain text-to-speech, transcription, and background removal?▼

Chain these tasks by running Kokoro TTS for narration, passing the audio to Whisper for transcription captions, and applying u2net for background removal to prepare all HyperFrames assets.

Where are downloaded TTS and transcription models cached for reuse?▼

Downloaded TTS, transcription, and background removal models are cached locally under the ~/.cache/hyperframes/ directory, allowing reuse across multiple video projects without re-downloading.

Why does the first run of text-to-speech or transcription take longer to start?▼

The first run takes longer because each command downloads its required model, such as Kokoro for TTS, Whisper for transcription, or u2net for background removal, before processing begins.