hyperframes-media

Create and manipulate multimedia assets within the HyperFrames platform.

Updated Feb 27, 2026

Search Tags:#text-to-speech #transcription #background removal #background music #caption authoring

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, transformers, torch, soundfile, u2net_human_seg, ffmpeg, espeak-ng, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the creation of multimedia assets for HyperFrames compositions, including text-to-speech, background music generation, transcription, background removal, and caption authoring.

Core Features & Use Cases

Text-to-Speech: Generate speech from text with multiple TTS providers, including HeyGen, ElevenLabs, and Kokoro.
Background Music: Create custom background music using Google Lyria and MusicGen.
Transcription: Convert audio to text with Whisper and manage caption timing.
Background Removal: Remove backgrounds from images and videos using u2net_human_seg.
Caption Authoring: Generate captions with style detection, word grouping, and positioning.
Use Case: If you need to create a video with a specific voiceover, background music, and captions, this Skill can handle all these tasks efficiently.

Quick Start

Use the hyperframes-media skill to transcribe the audio in 'video.mp4' and generate captions for it.

Frequently Asked Questions about hyperframes-media

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

FAQPage Schema

How do I generate speech from text and transcribe audio for video compositions?▼

Text-to-speech generation and audio transcription are handled using multiple TTS provider APIs and Whisper, converting input text to spoken audio and accurately transcribing audio tracks back to text within multimedia compositions.

What is the best way to remove backgrounds from images and videos for multimedia assets?▼

Background removal is processed using the u2net_human_seg model, which isolates human subjects from image and video assets to produce clean foreground layers for HyperFrames compositions.

Can I use HeyGen and ElevenLabs for text-to-speech generation in HyperFrames?▼

Yes, text-to-speech generation supports multiple providers including HeyGen, ElevenLabs, and Kokoro, allowing you to synthesize natural sounding voiceovers directly from input text.

How do I author captions with style detection and word grouping from transcribed audio?▼

Caption authoring generates styled captions from transcribed text by applying automatic style detection, word grouping, and precise positioning to synchronize text with audio tracks.

Do I need ffmpeg and espeak-ng installed to process background music and audio?▼

Yes, ffmpeg and espeak-ng are required dependencies alongside torch and soundfile to process audio manipulation, generate background music using Google Lyria and MusicGen, and manage multimedia assets.

Why does audio transcription require Whisper and how does it manage caption timing?▼

Audio transcription requires Whisper to accurately convert spoken audio into text and manage precise caption timing, ensuring generated text aligns correctly with the original audio track.