skills.rest
Kamalabot
KamalabotCOMMUNITY
Explore all skills by this author →
GitHub

hyperframes-media

Preprocess local media for HyperFrames with TTS, transcription, and background removal.

Updated Apr 25, 2026
Search Tags:#text-to-speech#captions#transcription#voiceover#background-removal#hyperframes#media-preprocessing
One-click install
npx skills add https://github.com/Kamalabot/tt-vid --skill hyperframes-media-kamalabot
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hyperframes-media
Source: https://github.com/Kamalabot/tt-vid/tree/main/man_lady/.agents/skills/hyperframes-media
Command: npx skills add https://github.com/Kamalabot/tt-vid --skill hyperframes-media-kamalabot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual effort of creating voiceover audio, timed captions, and transparent overlay assets for HyperFrames video compositions, removing the need for separate audio editing tools, transcription services, or video editing software for these tasks.

Core Features & Use Cases

  • Local Text-to-Speech Narration: Generate voiceover audio from text or script files using Kokoro-82M, with 54+ multilingual voices and no API key required.
  • Word-Level Timestamped Transcription: Convert audio or video files to timestamped caption data using Whisper, with support for multiple model sizes and language options.
  • Background Removal for Overlays: Remove backgrounds from video or image files to create transparent cutout assets for layered compositions, with optional plate layer generation for text-behind-subject effects.
  • Use Case: A tutorial creator can use this Skill to generate a voiceover from their script, transcribe it to get perfectly timed captions, and remove their background to float as a presenter overlay in a HyperFrames composition, all locally without paid tools.

Quick Start

Use the hyperframes-media skill to generate a voiceover from your text script, transcribe the audio into timestamped captions, and remove the background from your presenter video for use in a HyperFrames composition.

Frequently Asked Questions about hyperframes-media

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

FAQPage Schema
How do I generate text-to-speech voiceover audio locally without an API key?▼

You can generate text-to-speech voiceover audio locally by providing a text script to the Kokoro-82M engine, which supports 54+ multilingual voices and requires no API key. The system automatically caches models for offline narration generation.

How do I transcribe audio to word-level timestamped captions for video compositions?▼

To transcribe audio into word-level timestamped captions, the local Whisper engine processes your audio or video files. It supports multiple model sizes and language options to output caption data perfectly timed for video composition overlays.

Does local background removal work on video files for transparent overlay creation?▼

Yes, local background removal works on both video and image files to create transparent cutout assets for layered compositions. It also offers optional plate layer generation to achieve text-behind-subject overlay effects.

Can I prepare voiceovers, captions, and transparent presenter overlays without paid transcription services?▼

Yes, you can prepare voiceovers, captions, and transparent presenter overlays entirely without paid transcription services or separate audio editing tools. All media preprocessing operations run locally with automatic model caching, eliminating manual editing and API dependencies.

What is the best way to automate media preprocessing for HyperFrames video compositions?▼

The best way to automate HyperFrames media preprocessing is to run text-to-speech narration, Whisper transcription, and human subject background removal locally. This pipeline outputs assets formatted specifically for HyperFrames composition conventions without manual editing.

Related Skills

Explore More Content & Communication Skills→
geezerrrrgeezerrrr
117

openai-whisper

Transcribe audio and video files into text or SRT subtitles locally with Whisper CLI.

Community
Basic
compozycompozy
182

hyperframes-media

Generate TTS audio, word-timestamp transcripts, and transparent overlays for HyperFrames.

Official
Advanced
MuzeWinterMuzeWinter
1

hyperframes

Build HTML video compositions with timed clips, captions, and transitions.

Community
Advanced
xiaxianlinxiaxianlin
1

hyperframes-media

Preprocess multimedia assets with speech synthesis, transcription, and background removal.

Community
Intermediate