Embedded captions: cinematic talking-head subtitles burned into the scene
Add verbatim, cinematic or VFX-themed captions to a single-subject talking-head video, compositing peak words behind the subject — all locally
- What
- Add verbatim, cinematic or VFX-themed captions to a single-subject talking-head video, compositing peak words behind the subject — all locally
- Cost
- Free
- Needs
- Node, Bash, FFmpeg/ffprobe on PATH; Sharp, Puppeteer (with Chromium) and GSAP in the caption project (not inside the plugin); network once for the matting-model download (~168 MB); single-subject talking-head footage
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @heygen-com's HyperFrames embedded-captions skill: a full local pipeline that adds captions to an existing single-subject talking-head video without touching the footage. One catalog, picked up front (35 identities); three modes — Standard (verbatim lower-third rail + embed climax composited behind the subject at the peak), Cinematic (pure embed, hero typography composited into the scene), Theme (five themed constitutions: ordnance, terminal, neonsign, stardust, stomp). Everything runs locally end to end: WhisperX transcription via uvx, subject matting, safe-zone computation, frame-accurate preview sheets before the paid render, hard decision gates (refuses multi-speaker, caption-less, garbled or already-captioned clips), and non-negotiables (face never 100% covered, captions stay on-frame, ≥0.5s per caption, timing within 80ms). Needs Node, FFmpeg, Sharp, Puppeteer and GSAP; matting weights download once (~168 MB). Honest caveats: a large render costs minutes — visual QA on the preview sheet is mandatory before rendering; model quality varies with non-native speech; matte quality on busy handheld footage can flicker, so trim and probe first. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Embedded captions is a free Muse skill, the HyperFrames embedded-captions skill: a full local pipeline adding captions to an existing single-subject talking-head video without touching the footage. One catalog is picked up front with 35 identities, and three modes are offered: Standard, Cinematic with hero typography, and Theme with five themed constitutions.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox and failed · Nov 18, 2026 · Needs pnpm, npm cannot install it📌 Pinned version: commit a9823f7Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Node, Bash, FFmpeg/ffprobe on PATH; Sharp, Puppeteer (with Chromium) and GSAP in the caption project (not inside the plugin); network once for the matting-model download (~168 MB); single-subject talking-head footage Install "Embedded captions: cinematic talking-head subtitles burned into the scene" for me. The HyperFrames embedded-captions skill: adds verbatim, cinematic or themed captions to an existing single-subject talking-head video without editing the footage — rail + embed model, 35-identity catalog, five-step pipeline (init, prepare, author JSON, visual QA, render), decision gates and non-negotiables. Repository: https://raw.githubusercontent.com/heygen-com/hyperframes/a9823f719df9a18e1ed004bede9a138c8a9adfc5/skills/embedded-captions/SKILL.md Pinned version: install the code at commit a9823f719df9a18e1ed004bede9a138c8a9adfc5 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "embedded-captions". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the Sharp/Puppeteer/GSAP deps in the caption project, download the matting weights on first use). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- a9823f7 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox and failed · Nov 18, 2026 — Needs pnpm, npm cannot install it · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Oct 21, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.