magic-hour-talking-video SKILL.md skillA
magic-hour-talking-video from magichourhq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add magichourhq/skills/magic-hour-talking-video@v1.3.2Pins v1.3.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- magichourhq/skills
- Path
skills/magic-hour-talking-video/SKILL.md- Versions recorded
- 7
- Latest version
- v1.3.2, committed Oct 30, 2026
- First version recorded
- Sep 10, 2026
- Size
- 8,050 bytes
- Repository stars
- 13
- License
- MIT
Make a still portrait speak from supplied audio with Magic Hour Talking Photo, or lip-sync existing video to replacement audio. Use when Magic Hour is requested or configured and suitable. Both routes require audio; neither synthesizes speech from text. Preserve an explicitly requested alternative provider.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Magic Hour talking video Approve the spoken result before paying to animate a face. Lip sync cannot fix a mispronounced name or a sentence cut off by the timeline. Use the supplied portrait, speech and language without asking for them again. Choose technical settings and perform delegated creative checks yourself; respect requested script/voice approvals and the existing total budget. Show the finished clip first, with an outstanding listening or language check made explicit. For recurring presenters or language versions, read [speech and localization](references/localization.md). ## Select the source and route | Input and intent | Route | | ---------------------------------------------------- | ----------------------------------------------------------------- | | Still portrait image plus an existing audio file | `create_talking_photo` | | Existing speaker video plus a replacement audio file | `create_lip_sync_video` | …
Read the whole file at its exact version.
How to install
mdr add magichourhq/skills/magic-hour-talking-video@sha256:a643fc67ddbcea8eThe line at the top of this page pins the label v1.3.2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_vzodfmjtxooatb7d)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 10, 2026 and Oct 30, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.3.2 latest | 2026-10-30 | e549a80 | 8,050 B | A | view · diff |
| v1.3.2 | 2026-10-30 | 4a96b3a | 8,087 B | A | view · diff |
| v1.3.1 | 2026-10-21 | e43c205 | 8,087 B | A | view · diff |
| v1.3.0 | 2026-10-13 | 32ddedb | 7,740 B | A | view · diff |
| v1.2.0 | 2026-09-11 | e2a1643 | 6,419 B | A | view · diff |
| v1.1.0 | 2026-09-11 | 19e81ac | 5,461 B | A | view · diff |
| v1.0.0 | 2026-09-10 | 5307d79 | 4,637 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8050 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
magichourhq/skills · 13 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vzodfmjtxooatb7d GET https://markdownregistry.com/api/v1/resolve?ref=magichourhq/skills/magic-hour-talking-video GET https://markdownregistry.com/api/v1/blob/a643fc67ddbcea8ea04299e366c61ffb7cf61cd85e29fe0daacdd57dde1bc4f6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.