skills.rest
hoanghd218
hoanghd218COMMUNITY
Explore all skills by this author →
GitHub

hyperframes-media

Generate local voiceovers, transcripts, and background-removed overlays with CLI commands.

7|9|Updated May 9, 2026
Search Tags:#automation#captions#transcription#tts#video-processing#background-removal
One-click install
npx skills add https://github.com/hoanghd218/claude-code-2-days --skill hyperframes-media
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hyperframes-media
Source: https://github.com/hoanghd218/claude-code-2-days/tree/main/.agents/skills/hyperframes-media
Command: npx skills add https://github.com/hoanghd218/claude-code-2-days --skill hyperframes-media

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate local voiceover, transcripts, and background-removed overlays for HyperFrames compositions, enabling offline workflows without API calls.

Core Features & Use Cases

  • Text-to-speech narration generation using Kokoro voices for video assets.
  • Audio/video transcription and caption generation with Whisper, including timestamps.
  • Background removal to create transparent overlays (u2net) for flexible composition.
  • Automatic model download and caching on first run, with outputs drop-in to project workflows.

Quick Start

Use the tts command to generate narration, then transcribe to create captions, and finally remove-background to produce a transparent overlay for your 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 local text-to-speech voiceover for video assets without an API?▼

Generate local text-to-speech voiceover offline using the Kokoro-based TTS voices provided by the tts command. This enables local voiceover generation for video assets without requiring external API calls.

Can I create video captions and transcriptions with timestamps locally?▼

Create video captions and transcriptions locally using the transcribe command with Whisper transcription models. This generates accurate audio and video transcription outputs that include timestamps for caption creation.

How do I remove backgrounds from media assets to create transparent overlays?▼

Remove backgrounds from media assets to create transparent overlays using the remove-background command. This utilizes the u2net background removal model to produce flexible transparent overlays for composition.

Do I need to manually download models to run transcription and TTS commands?▼

You do not need to manually download models to run transcription and TTS commands. The deterministic CLI commands automatically download required models on first run and cache them under ~/.cache/hyperframes.

What is the best way to prepare offline narration, captions, and overlays for compositions?▼

The best way to prepare offline narration, captions, and overlays is using deterministic CLI commands for TTS, transcription, and background removal. This produces drop-in outputs for direct consumption by your composition workflows.

Are there limitations to using local TTS and background removal models for video processing?▼

Limitations of using local TTS and background removal models include requiring initial setup time for automatic model downloads and local storage space. Models are cached under ~/.cache/hyperframes for subsequent offline video processing runs.

Related Skills

Explore More Design & Creative Skills→
boraoztuncboraoztunc
248

hyperframes-media

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

Community
Intermediate
compozycompozy
182

hyperframes-media

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

Official
Advanced
cosmicstack-labscosmicstack-labs
364

hyperframes-media

Generate local TTS audio, word-timestamp transcripts, and transparent overlays for media compositions.

Official
Intermediate
enclawedenclawed
2

openai-whisper

Transcribe audio files to text locally using the Whisper CLI.

Community
Basic