Skip to main content
skill CX Codex

layer-localization — Claude Code skill for media localization

The layer-localization Claude Code skill prepares video and image assets for multiple languages. It activates for dubbing, voice-over, burned-in captions, or text changes derived from an approved master.

MIT 1,100 installs ★ 10 updated 2026-09-30

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add layerai/skills --skill layer-localization -a claude-code
Open on GitHub

What layer-localization does

The skill maps an approved master asset to localized versions of a video or image. It handles dubbing, speech from translated copy, burned-in subtitles, and text replacement in artwork. Each language version should come from the master, not from another translation. Translations can come from the user or their localization vendor; copy drafted by the skill should be marked for review.

Before the first run, estimate the full language matrix and apply the 20 CU gate to its total. Use get_base_model to check supported languages, subtitle presets, and model behavior. The layer skill handles generation and estimates. Exact image lettering uses layer-typography; video timeline edits use layer-video-timeline.

Dub models either preserve clip length or adjust it while syncing lips. The latter behavior changes duration, so it does not fit a fixed-length slot. For speech synthesis, the language can be set explicitly. Check rendered text for overflow and missing glyphs; unsupported characters may appear as empty boxes.

What it helps with

  • dub a video into another language
  • create voice-over from translated copy
  • burn subtitles into a language-specific video
  • replace text in an image for another market
  • fix overflowing copy or missing font glyphs

Example prompts for the agent

  • Dub this video into German and keep the original duration.
  • Create a voice-over in another language from this translated script.
  • Replace the image text for each language version.

How to install layer-localization

1Skills CLI (Vercel)

npx skills add layerai/skills --skill layer-localization -a claude-code

2Manually: put the files in place

~/.claude/skills/layer-localization/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/layer-localization/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about layer-localization

How do I install layer-localization in Claude Code?

Run npx skills add layerai/skills --skill layer-localization -a claude-code. The skill file is at ~/.claude/skills/layer-localization/SKILL.md.

What does layer-localization do?

It helps create localized video and image assets, including dubbed audio, voice-over, burned-in subtitles, and replaced artwork text.

Which other skills does layer-localization need?

layer handles generation and estimates. Use layer-typography for exact image lettering and layer-video-timeline for video timeline edits.

Source text

SKILL.md · MIT
---
name: layer-localization
description: "Use when one approved Layer asset must ship in several languages: dubbing a trailer or ad, voice-over in another language, burned-in subtitles or captions per market, or translating text that appears in an image, end card, store screenshot, or UI. Also when a dub drifts out of sync, translated copy no longer fits, or a font shows empty boxes for another script. Keywords: localisation, localization, dubbing, translation, subtitles, captions, voice-over, multilingual, markets, CJK, RTL."
license: MIT
---

# Layer Localization

## Overview

Localisation is one master multiplied by a list of languages. Every language version comes from the
approved master, never from another language's version: a German cut made from the French cut carries
the French cut's defects into German.

Layer covers three layers of an asset:

- **Voice**: dub an existing video, or speak a translated script with text to speech.
- **Captions**: burn subtitles into a video.
- **Text in images**: replace words in the art, or letter a clean plate per language.

Generation mechanics, the estimate gate and polling are in the `layer` skill. Setting exact type is
`layer-typography`, and cutting finished videos is `layer-video-timeline`.

If a sibling skill named here is missing from your available skills, ask the user to install it
(`npx skills add layerai/skills --skill <name>`); unattended, proceed from tool schemas and flag the
gap.

## Quick reference

| Job                                   | Route                                                                       |
| ------------------------------------- | --------------------------------------------------------------------------- |
| Dub a voiced video                    | `use_case: "dub_video"`, `target_language` from the model's `dub_languages` |
| New voice-over from a translated line | `use_case: "text_to_speech"`, `speech_language` from `speech_languages`     |
| Burn in captions                      | `use_case: "video_subtitle"`, `subtitle_preset` from `subtitle_presets`     |
| Change words baked into an image      | `use_case: "edit_text"`                                                     |
| Exact text per language on clean art  | `render_text`, then `compose_image` (`layer-typography`)                    |

Every route is a `list_base_models` filter except the last, which is two deterministic tools that
spend no Creative Units. Read `get_base_model` on the chosen model before the first run: the
language lists, presets and behaviour below live in its capabilities.

## Plan the matrix first

Before any run, write down assets by languages: each master `file_id`, each language's code, and
an empty cell for each output `file_id`. Languages are ISO 639-1 codes (`de`, `ja`, `pt`), which
name a language, not a market. If the user needs Brazilian rather than European Portuguese, say that
a code alone may not distinguish them and check the model's list.

Get approved translations from the user or their localisation vendor. If you translate copy yourself,
label it a draft for review: store copy, legal lines and character names are the user's call.

Price the whole matrix before the first run, and apply the 20 CU gate to the total. Pricing reads the
files, so pass each source to the estimate. Text to speech is priced per character, so each
language's script is its own estimate. When in doubt whether two languages price apart, estimate one
call per language.

## Voice

**Dubbing** keeps the original performance and changes its language. `target_language` is required on
dub models and must be one of the codes in `dub_languages`. Dub models differ in one decision that
matters more than voice quality:

- Some leave the picture and its length exactly as they are. Choose these when the dub goes back over
  an existing edit, a timeline, or a fixed-length ad slot.
- Others re-sync the lips and may lengthen or shorten the clip to the new language's pace. Choose
  these for an on-screen presenter, never for a clip that must keep its length.

The tool schema currently names ElevenLabs Dubbing for the first behaviour and HeyGen models for the
second; confirm with `get_base_model`, since the catalogue changes.

**Text to speech** suits a fresh voice-over from a translated script. Leave `speech_language` unset
and the model guesses from the text; set it when lines are short or full of names and loanwords,
which are exactly what a model reads in the wrong language. `text_normalization` controls how numbers
and dates are read, which differs by language. Reuse the same voice choices across a language's
lines so the character does not change voice mid-campaign.

Translated speech runs longer. German and French lines often outgrow the English, and a 15-second
slot does not stretch. Shorten the line, not the pacing: a small speed nudge is fine, a crammed read
is not.

## Captions

Filter for `use_case: "video_subtitle"`. Spell `subtitle_preset` exactly as one of the model's
`subtitle_presets`: any other name is quoted at the default style and then refused at launch. Presets
listed under `subtitle_dynamic_presets` animate word by word and bill at a higher rate, so pass the
same preset to the estimate. `subtitle_alignment`, `subtitle_color` and `subtitle_secondary_color`
apply only where the capabilities report them. The schema takes no caption text, so caption each
language's dub rather than the master, and confirm in `get_base_model` that the model captions that
language. For a dub or caption run, attach the source video in the guidance slot `get_base_model`
lists for the model; do not assume one.

Burned-in captions make one file per language, so keep the master without captions. Move captions to the
top when the lower third carries a CTA, gameplay UI or a lower-third title.

## Text in images

The cheapest localisation is art with no words baked in. Generate the master clean and letter each
language with `render_text` and `compose_image`.

Copy burned into a video frame, such as an end card, is out of reach of image tools. Ask for the
text-free end card first. Failing that, cover the end-card span on a `render_video_timeline` edit
(`layer-video-timeline`): an image or solid item over the old copy, and a text item set in the
language's font with `font_file_id`.

- **Script coverage.** A Latin brand font usually has no CJK, Cyrillic, Thai or Arabic glyphs, and
  missing glyphs render as empty boxes. Pick a family that covers the script (a Google Fonts family
  name in `font_family` works) and look at every render.
- **Direction and shaping.** For right-to-left and joined scripts, check visually that letters join
  and run in the right direction. If they do not, report it rather than ship it.
- **Expansion.** Size the text box for the longest language and render every language into the same
  box. When `render_text` refuses copy with the size it needs, shorten the copy or lower `font_size`
  consistently across the set, so one market's title is not visibly smaller.

When the words are already baked in, run an `edit_text` model on the master with the exact
replacement string quoted. Check it letter by letter. If it fails, remove the text once to a clean
plate (an `erase_object` or `inpainting` model) and letter the plate per language.

## Worked example

"Localise our 15-second 9:16 trailer and its end card into German, Japanese and Portuguese."

1. Matrix: trailer and end card masters by `de`, `ja`, `pt`. Ask whether Portuguese means Brazil,
   and for approved translations of the end card's two lines.
2. `list_base_models` with `use_case: "dub_video"`; `get_base_model` on candidates. The trailer must
   stay 15 seconds, so pick one that keeps picture and length, and confirm all three codes are in its
   `dub_languages`.
3. Estimate all three dubs with the trailer attached. The end cards need no estimate: they are deterministic.
   Present the total; above 20 CUs wait for an explicit yes.
4. `execute_forge` per language with `target_language`; poll each with `get_forge_run` at
   `poll_interval_seconds`. Watch each dub against the picture.
5. End card: the master has no text, so `render_text` each language into one shared box, the
   Japanese with a family that covers kana and kanji, then `compose_image` onto the master.
6. Fill the matrix with every output `file_id` and hand it over.

## Common mistakes

- Localising from another language's version instead of the master.
- A lip-resyncing dub dropped into a fixed-length edit, which then runs long or short.
- Estimating one language and assuming the rest cost the same.
- A brand font that lacks the script, shipped with empty boxes.
- Letting each language shrink its own font size until its copy fits.
- Translating store or legal copy and presenting it as final.
- Burning captions into the only copy of the master.

© layerai · MIT · layerai/skills

Similar skills

All skills for Marketing and content →

From the same set33

The whole set →
layer-textures layer-textures generates repeating textures via Layer API with a tileability filter that eliminates edge seams. Built for game engine materials, trim sheets, and pattern fills. CX Codex +1 4,900installs layer-image layer-image — a skill for text-to-image runs through Layer: what to put in the prompt, how to set aspect ratio, and when to upload a reference instead of describing it. CX Codex +1 4,900installs layer-workflow-import layer-workflow-import converts third-party node graphs, exported pipelines, or prose descriptions into Layer Blueprint workflows. Helps migrate external AI pipelines directly into Layer. CX Codex +1 4,000installs layer-live-ops layer-live-ops — a Claude Code skill for producing art content for live games. It handles item evolution, upgrade chains, currency packs, and seasonal reskins. CX Codex +1 1,100installs layer-ua-creatives layer-ua-creatives — a skill for Claude Code that orchestrates game performance ad production on Layer. Builds variant testing matrices across static concepts, motion, reframed aspect ratios, and CTA cards. CX Codex +1 1,100installs layer-store-assets The layer-store-assets Claude Code skill helps prepare store artwork for games and apps. It covers icons, screenshot sets, Steam capsules, feature graphics, and preview videos. CX Codex +1 1,100installs layer-motion-templates layer-motion-templates — a Claude Code skill for creating Layer video templates with media slots for batch rendering. Runs when generating ad variants with swappable hooks, localizations or voice-overs. CX Codex +1 1,100installs layer-motion-graphics The layer-motion-graphics Claude Code skill creates motion graphics in Layer, from logo reveals to animated titles. It places words on a timeline and moves them with transitions or a separate video clip. CX Codex +1 1,100installs

Project sponsors

Companies that keep this analytics open