skills.rest
cvenwu
cvenwuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

hyperframes-media

Generate local TTS narration, word-level transcripts, and transparent overlays for HyperFrames.

Updated Aug 23, 2026
Search Tags:#captions#transcription#tts#voiceover#background-removal#hyperframes
One-click install
npx skills add https://github.com/cvenwu/AiFlow --skill hyperframes-media-cvenwu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hyperframes-media
Source: https://github.com/cvenwu/AiFlow/tree/main/skills/hyperframes-media
Command: npx skills add https://github.com/cvenwu/AiFlow --skill hyperframes-media-cvenwu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Asset preprocessing for HyperFrames, enabling local generation of narration, transcription, and background removal to streamline video compositions.

Core Features & Use Cases

  • Text-to-Speech: generate narration locally using Kokoro voices without external APIs.
  • Transcription & Captions: produce time-stamped transcripts with word-level timing using Whisper.
  • Background Removal: create transparent overlays by isolating subjects with u2net.

Quick Start

Run the tts, transcribe, and remove-background commands to produce narration, captions, and transparent overlays for your HyperFrames project.

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 TTS narration for video compositions without external APIs?▼

Generate local TTS narration by running the tts command, which uses Kokoro voices to produce audio assets without external APIs. This enables offline-friendly voiceover generation for your HyperFrames productions.

Can I transcribe speech with word-level timing to create captions locally?▼

Yes, transcribe speech with word-level timing using the transcribe command, which uses Whisper to produce time-stamped transcripts. This generates accurate caption assets for video compositions.

What's the best way to remove backgrounds and create transparent overlays for video assets?▼

Remove backgrounds to create transparent overlays by running the remove-background command, which isolates subjects using u2net. This produces composited scene assets for HyperFrames productions.

Do I need an internet connection to run TTS, transcription, and background removal?▼

An internet connection is only needed for the first use to download models, which are then cached under ~/.cache/hyperframes. Subsequent TTS, transcription, and background removal tasks run offline.

How does local asset preparation streamline HyperFrames video compositions?▼

Local asset preparation streamlines HyperFrames video compositions by generating narration, transcription, and background removal in one workflow. This enables end-to-end asset preparation for voiceover, captions, and overlays.

Are there limitations when using Kokoro voices and Whisper for local media asset preparation?▼

Limitations include requiring sufficient storage for models downloaded on first use and cached under ~/.cache/hyperframes. The local TTS, transcription, and background removal workflow depends on these cached models.

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
chmonitorchmonitor
255

hyperframes-media

Generate audio, captions, and background-removed visuals for HyperFrames video compositions.

Official
Advanced
automatedigitalautomatedigital
1

hyperframes-media

Generate voiceovers, transcribe media, and remove backgrounds for HyperFrames compositions.

Official
Intermediate
hoanghd218hoanghd218
7

hyperframes-media

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

Community
Intermediate