Hyperframe Pro Voice

Voice-over for a HyperFrames video, and every revision that touches it. Generate ONE continuous take with word-level timestamps, anchor every animation cue to a spoken word, cap pauses to hit a duration ceiling, and swap a single line inside a finished take without re-recording. Use for TTS, for "it's too long", for "change this line / the CTA", and for any edit to a video that already rendered.

49 stars 5 forksImages, Video & Audio Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add buildwithhanif/hyperframe-pro

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add buildwithhanif/hyperframe-pro --skill hyperframe-pro-voice
Manual install
git clone --depth 1 https://github.com/buildwithhanif/hyperframe-pro.git /tmp/hyperframe-pro
mkdir -p ~/.claude/skills
cp -r /tmp/hyperframe-pro/plugins/hyperframe-pro/skills/hyperframe-pro-voice ~/.claude/skills/hyperframe-pro-voice

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Voice, timing, and revisions

The voice-over is not a soundtrack laid under the animation — it is the **clock the animation runs on**.
Get one take with word-level timestamps and every cue in the video anchors to a word, so the number lands
on the number and the title card lands on "three".

## One take. Always.

One TTS call for the entire script. Not one per scene, not one per step.

Per-scene narration produces an audible seam at every join, a flat list-like delivery, and a timing model
that drifts the moment any scene changes length. One take also gives you one continuous word table, which
is what makes cue-chaining possible.

Request **word-level timestamps** (`/with-timestamps` on ElevenLabs). Without them you are placing cues by
stopwatch, and every script edit re-times the whole video by hand.

```bash
node ${CLAUDE_PLUGIN_ROOT}/scripts/tts.mjs script.json <projectDir>/assets/vo
```

Writes `vo.wav` (44.1k mono, normalised) plus `audio_meta.json` carrying every word with `start`/`end`.

## Anchor cues to words, never to nth-occurrence

Resolve each cue by "the next occurrence of this word AFTER the previous cue", chained:
Read the full skill on GitHub

Details

Skill name
hyperframe-pro-voice
Path
plugins/hyperframe-pro/skills/hyperframe-pro-voice/SKILL.md
License
MIT
Repo updated
11 October 2026

FAQ

What does the Hyperframe Pro Voice skill do?

Voice-over for a HyperFrames video, and every revision that touches it. Generate ONE continuous take with word-level timestamps, anchor every animation cue to a spoken word, cap pauses to hit a duration ceiling, and swap a single line inside a finished take without re-recording. Use for TTS, for "it's too long", for "change this line / the CTA", and for any edit to a video that already rendered.

How do I install the Hyperframe Pro Voice skill?

Claude Code plugin: /plugin marketplace add buildwithhanif/hyperframe-pro. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Hyperframe Pro Voice popular?

It lives in buildwithhanif/hyperframe-pro, which has 49 GitHub stars and 5 forks.

Related skills

Hyperframe Pro

49

buildwithhanif/hyperframe-pro

Turn a TOPIC or PROMPT into a finished vertical explainer video — script, voice-over, animation, captions, render. Use on "make me a video about X", "turn this topic into a reel", "prompt to video", "short-form explainer", "faceless video", or when someone hands over a subject and wants an MP4. Also handles REVISIONS to a video built this way: "edit the video", "change this line", "it's too long", "the hook is weak". Built on HyperFrames (HTML → MP4). This is the PRODUCTION layer: it decides what the video should do before any code is written, then enforces it mechanically.

Images, Video & Audio

Hyperframe Pro Beats

49

buildwithhanif/hyperframe-pro

Decide what each beat of a video SHOWS before writing any generator code — the job, the hero visual, the framing, the zones. Includes the retention rules the lint enforces: no dead air, hero-sized heroes, a visual may not outstay its step, and the three registers a hook can be in. Use after the script exists and before the generator, or when a finished video "looks like slides" / "feels like decoration".

Images, Video & Audio

Hyperframe Pro Footage

49

buildwithhanif/hyperframe-pro

Generate photoreal video plates for beats a drawing cannot sell — a theft, a loss, an accident — using fal.ai (gpt-image-2 for the first frame, minimax h3-max for the motion). Includes the prompt recipe that makes a plate read as real, the wiring rules for putting video into a HyperFrames composition, how to cut a multi-shot opening, and the safety rules that keep this from producing convincing fake evidence.

Images, Video & Audio

Suno Song Creator

43

nwp/suno-song-creator-plugin

This skill should be used when the user asks to "create a Suno prompt", "write a Suno song", "generate music with Suno", "help me with Suno", "make a song prompt", "create lyrics for Suno", "build a music prompt", or mentions Suno AI music generation. Provides comprehensive guidance for creating professional Suno prompts using advanced prompting strategies, structured formatting within 1000 character limit (NO blank lines between sections), parameter optimization, genre-specific techniques, interactive questioning with efficient project name collection, automated artist/song research via sub-a

Images, Video & Audio

Hyperframe Pro Script

49

buildwithhanif/hyperframe-pro

Turn a topic, prompt or research brief into ONE continuous narration script for a short-form explainer video — written for the ear, hook complete in the first two seconds, sized to fit under the 2:59 ceiling. Use when starting a video from a subject rather than from existing copy, or when a script reads flat, rushed, or like someone reading a document out loud.

Images, Video & Audio

AI Video Creation

79

LeadMagic/gtm-skills

AI-powered video creation for marketing — step-by-step workflows for HeyGen (AI spokespersons), Synthesia (AI avatars), Runway (generative video), Captions (AI editing), Opus Clip (AI clipping), ElevenLabs (AI voiceover), and Descript (AI editing). Use when creating demo videos, personalized outreach videos, social video content, ads, or scaling video production without a video team. Triggers on: "AI video", "HeyGen", "Synthesia", "Runway AI", "AI spokesperson video", "AI ads".

Images, Video & AudioIn 1 list18

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.