lilimozi/oh-plugins/hyperframes-media

HyperFrames Media Preprocessing

Three CLI commands that produce assets for compositions: tts (speech), transcribe (timestamps), and remove-background (transparent video). Each downloads a model on first run and caches it under ~/.cache/hyperframes/. Drop the output into the project, then reference it from the composition HTML — see the hyperframes skill for the audio/video element conventions.

Text-to-Speech (tts)

Generate speech audio locally with Kokoro-82M. No API key.

npx hyperframes tts "Text here" --voice af_nova --output narration.wav
npx hyperframes tts script.txt --voice bf_emma --output narration.wav
npx hyperframes tts --list                       # all 54 voices

Voice Selection

Match voice to content. Default is af_heart.

Multilingual

Voice IDs encode language in the first letter: a=American English, b=British English, e=Spanish, f=French, h=Hindi, i=Italian, j=Japanese, p=Brazilian Portuguese, z=Mandarin. The CLI auto-detects the phonemizer locale from the prefix — no --lang needed when the voice matches the text.

npx hyperframes tts "La reunión empieza a las nueve" --voice ef_dora --output es.wav
npx hyperframes tts "今日はいい天気ですね" --voice jf_alpha --output ja.wav

Use --lang only to override auto-detection (stylized accents). Valid codes: en-us, en-gb, es, fr-fr, hi, it, pt-br, ja, zh. Non-English phonemization requires espeak-ng system-wide (brew install espeak-ng / apt-get install espeak-ng).

Speed

• 0.7-0.8 — tutorial, complex content, accessibility
• 1.0 — natural pace (default)
• 1.1-1.2 — intros, transitions, upbeat content
• 1.5+ — rarely appropriate; test carefully

Long Scripts

For more than a few paragraphs, write to a .txt file and pass the path. Inputs over ~5 minutes of speech may benefit from splitting into segments.

Requirements

Python 3.8+ with kokoro-onnx and soundfile (pip install kokoro-onnx soundfile). Model downloads on first use (~311 MB + ~27 MB voices, cached in ~/.cache/hyperframes/tts/).

Transcription (transcribe)

Produce a normalized transcript.json with word-level timestamps.

npx hyperframes transcribe audio.mp3
npx hyperframes transcribe video.mp4 --model small --language es
npx hyperframes transcribe subtitles.srt          # import existing
npx hyperframes transcribe subtitles.vtt
npx hyperframes transcribe openai-response.json

Language Rule (Non-Negotiable)

Never use `.en` models unless the user explicitly states the audio is English. .en models (small.en, medium.en) translate non-English audio into English instead of transcribing it. This silently destroys the original language.

1. Language known and non-English → --model small --language <code> (no .en suffix)
2. Language known and English → --model small.en
3. Language unknown → --model small (no .en, no --language) — whisper auto-detects

Default model is `small`, not `small.en`.

Model Sizes

Music with vocals: start at medium minimum; produced tracks often need manual SRT/VTT import. For caption-quality checks (mandatory after every transcription), the cleaning JS, retry rules, and the OpenAI/Groq API import path, see hyperframes/references/transcript-guide.md.

Output Shape

Compositions consume a flat array of word objects. The id field (w0, w1, ...) is added during normalization for stable references in caption overrides; it's optional for backwards compatibility.

[
  { "id": "w0", "text": "Hello", "start": 0.0, "end": 0.5 },
  { "id": "w1", "text": "world.", "start": 0.6, "end": 1.2 }
]

Background Removal (remove-background)

Remove the background from a video or image so the subject (typically a person — avatar, presenter, talking head) sits as a transparent overlay in a composition.

npx hyperframes remove-background subject.mp4 -o transparent.webm  # default: VP9 alpha WebM
npx hyperframes remove-background subject.mp4 -o transparent.mov   # ProRes 4444 (editing)
npx hyperframes remove-background portrait.jpg -o cutout.png       # single-image cutout
npx hyperframes remove-background subject.mp4 -o subject.webm \
  --background-output plate.webm                                   # both layers in one pass
npx hyperframes remove-background subject.mp4 -o transparent.webm --device cpu
npx hyperframes remove-background --info                           # detected providers

Uses u2net_human_seg (MIT). First run downloads ~168 MB of weights to ~/.cache/hyperframes/background-removal/models/.

Layer separation (--background-output)

Pass --background-output (or -b) to emit a second transparent video alongside the cutout: same source RGB, alpha is 255 − mask instead of mask. The cutout is the subject with a transparent background; the plate is the original surroundings with a transparent hole where the subject was.

Both outputs share the same --quality preset and run from a single inference pass — encode cost roughly doubles, segmentation cost stays the same. Only valid for video inputs and .webm/.mov outputs.

Hole-cut plate, not an inpainted clean plate. The subject region in plate.webm is fully transparent — composite something opaque under it to fill the hole. The single test for whether --background-output is the right tool: _will anything ever be visible through the subject's silhouette where the subject used to be?_

If a user asks for "the room with the person removed" and intends to display it standalone, do not reach for --background-output. Tell them they need an inpainter.

Typical layered composition (the canonical hole-cut use case):

<!-- z=1 the inverse-alpha plate fills everything except the subject region -->
<video
  src="plate.webm"
  data-start="0"
  data-duration="6"
  data-track-index="0"
  muted
  playsinline
></video>
 
<!-- z=2 graphics / text live between the two layers -->
<h1 id="headline" style="z-index:2; ...">MAKE IT IN HYPERFRAMES</h1>
 
<!-- z=3 the cutout floats the subject back over the headline -->
<div class="cutout-wrap" style="position:absolute;inset:0;z-index:3">
  <video
    src="subject.webm"
    data-start="0"
    data-duration="6"
    data-track-index="1"
    muted
    playsinline
  ></video>
</div>

This is functionally equivalent to the text-behind-subject pattern below, but you don't need the original presenter.mp4 in the project — the plate replaces it. Useful when you want to ship just the two transparent layers and let the user drop arbitrary content between them.

Output Format

Chrome decodes VP9 alpha natively, so the .webm plugs into a composition like any other muted-autoplay video — see the hyperframes skill for the <video> track conventions.

Quality presets

--quality fast|balanced|best controls only the VP9 encoder's CRF — segmentation quality is fixed.

Compositing patterns — pick the right one

The cutout webm is a re-encoded copy of the source mp4's RGB. That choice has consequences depending on what you put behind it: