Skip to main content
skill CX Codex

layer-talking-characters — Claude Code skill: what it does

layer-talking-characters — a Claude Code skill for generating character speech and matching lip movements to audio. It handles presenter clips, UGC-style ads, cutscene dialogue, and new lines synced to existing footage.

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-talking-characters -a claude-code
Open on GitHub

What layer-talking-characters does

This skill builds a talking clip by pairing a voice with an image or video and syncing the mouth to the audio. It can generate speech first with text_to_speech, then pass that audio to a lip-sync model. Use image_to_video_lipsync for an approved still or video_lipsync for existing footage; get_base_model supplies the required input slots.

The face should be near-frontal, unobstructed, and large enough to read in frame. If a line exceeds the model’s maximum clip length, split it across shots instead of speeding up the delivery. Lip-sync pricing depends on source length, and estimates above 20 CUs require approval before the run. Separate skills cover speech craft and timeline assembly: layer-audio and layer-video-timeline.

What it helps with

  • sync a character’s mouth to a new line
  • create speech for a presenter in a UGC-style ad
  • fit dialogue to a model’s clip limit
  • keep one character’s voice consistent across shots
  • lip-sync a new line to existing footage

Example prompts for the agent

  • Create a presenter for a UGC-style ad and sync the mouth to this line.
  • Match a new line to this footage without speeding up the delivery.
  • Sync the character’s dialogue to the mouth movement in this trailer shot.

How to install layer-talking-characters

1Skills CLI (Vercel)

npx skills add layerai/skills --skill layer-talking-characters -a claude-code

2Manually: put the files in place

~/.claude/skills/layer-talking-characters/SKILL.md

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

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

Questions about layer-talking-characters

How do I install layer-talking-characters in Claude Code?

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

What does layer-talking-characters do?

It helps generate speech for a presenter or character and sync mouth movement to audio in a still-based clip or existing footage. It also accounts for line length and model clip limits.

Which lip-sync route does layer-talking-characters use?

Choose image_to_video_lipsync when starting from an approved still, or video_lipsync for existing footage. If there is no audio yet, generate speech with text_to_speech first.

Source text

SKILL.md · MIT
---
name: layer-talking-characters
description: "Use when a character or presenter on Layer has to speak on camera: a talking-head presenter, a UGC-style ad, a character delivering dialogue in a cutscene or trailer, or lip-syncing existing footage to a new line. Also when the mouth drifts out of sync, a line overruns the clip, or a voice changes between shots. Keywords: lip sync, lipsync, talking head, presenter, UGC, spokesperson, dialogue, voice over, avatar, talking character."
license: MIT
---

# Layer Talking Characters

## Overview

A talking clip is two assets that must agree: a voice and a face. Make the voice first. The line's
length, pacing and emphasis then decide the clip, and the face is fitted to the audio rather than the
audio squeezed into a clip that was cut too short. Most failed talking clips are a good face on a
line that never fitted it.

Speech craft (scripts, pacing, invented names) is in `layer-audio`; animating a still is in
`layer-video`; assembling shots with captions and an end card is `layer-video-timeline`. The loop and
spend gate are in the `layer` skill.

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

| Starting point                       | Route                                                                           |
| ------------------------------------ | ------------------------------------------------------------------------------- |
| A script, no audio yet               | `use_case: "text_to_speech"` first                                              |
| An approved still plus the line      | `use_case: "image_to_video_lipsync"`                                            |
| Existing footage plus a new line     | `use_case: "video_lipsync"`                                                     |
| Speech generated with the picture    | `image_to_video` or `text_to_video` with `capabilities: {generate_audio: true}` |
| Any lip-sync model                   | `filter.capabilities: {lipsync: true}` narrows to them                          |
| Music or ambience under the dialogue | `layer-audio`, then mix in `layer-video-timeline`                               |

## The voice

Filter `list_base_models` for `use_case: "text_to_speech"`. The spoken line goes in `prompt`, which is
why speech prices by prompt length. Read `get_base_model` for what the model takes:

- `speech_language`, as one of its `speech_languages` codes, whenever a name or a short line could
  be read in the wrong language.
- `style_instructions` for delivery ("warm, unhurried, a smile in the voice") on the models that
  take it; it is free text, separate from the spoken line.
- `stability`, `similarity_boost`, `speed` and `style_exaggeration` where listed.

Hold one voice per character for the whole project. If the workspace keeps a trained voice as a
reference set, attach it with `reference_sets` and check that `reference_set_contributions` reports
`voice_applied`; when it does not, the line was read by a default voice, so say so. Never present a
degraded set as applied.

Write lines to be heard: short sentences, real punctuation for pauses, numbers and names spelled the
way they are said. A presenter's line runs at speaking pace, so before generating, check the line
against the clip lengths the lip-sync model accepts (`get_base_model`). A line longer than the
longest clip is two shots, not a faster read.

## The face

Lip sync works on what it can see. Frame for it:

- Face visible and near-frontal, mouth unobstructed: no hand, microphone, mask or hair across it.
- Head and shoulders or a medium close-up. A full-body wide shot leaves the mouth a few pixels tall.
- A neutral, slightly open mouth in the source still, so the model is not fighting a fixed grin.
- Even light on the face. Hard shadow across the mouth reads as jitter.

For `image_to_video_lipsync`, generate or approve the still with `layer-image` first. For
`video_lipsync`, choose footage where the speaker faces camera for the whole stretch being synced.

## Wiring the run

Lip-sync models differ in where they read inputs. The schema does not fix whether the audio goes in
`reference_audio` or `init_audio`, or the picture in `first_frame`, `init_image` or `init_video`.
Read the slots from `get_base_model` and use exactly those, as `guidance_files` entries of
`{file_id, type}`. To keep only models that take a given pair, filter with
`filter.guidance_file_types`, such as `["init_video", "reference_audio"]`.

The voice output from the speech run already has a `file_id`; pass it straight in. Upload only
local audio or footage, with `request_file_upload_url`.

The forge guide prices a lipsync by its source's length, so estimate with the real audio and picture
attached. A batch of lines is one estimate per distinct length, summed, and asked about above 20 CUs
before the first run.

## Honesty in ads

A generated presenter is not a customer. Do not script one as a real user's testimonial, give it
invented credentials, or caption it as a review. UGC-style is a format (handheld, direct to camera,
casual), not a claim that the speaker exists. Flag a brief that asks for a fabricated testimonial
before generating, and follow the user's disclosure policy for synthetic people.

## Worked example

"A 10-second UGC-style ad: our presenter says 'I didn't expect a puzzle game to get me this hooked.
Three hundred levels later, still going.'"

1. Flag the honesty point: the line reads as a personal testimonial. Ask whether to frame it as the
   presenter's own voice for the brand, and proceed with the user's answer.
2. `list_base_models` with `filter.use_case: "text_to_speech"`; `get_base_model` for languages and
   delivery fields. Script it clean: "I didn't expect a puzzle game to get me this hooked. Three
   hundred levels later... still going." `style_instructions`, where taken: "casual, amused, fast
   start, slower on the last three words".
3. The presenter still exists (`file_id` from an approved run): medium close-up, facing camera,
   mouth clear.
4. `list_base_models` with `filter.use_case: "image_to_video_lipsync"`; `get_base_model` for its
   slots and longest clip. The line runs about six seconds, so it fits one clip.
5. Estimate the speech run and gate it. The lipsync is priced by audio that does not exist yet, so
   tell the user it will be estimated as a second step. Run speech, poll at `poll_interval_seconds`.
6. Estimate the lipsync with the still and the real audio `file_id` in the slots `get_base_model`
   named; gate it above 20 CUs; execute and poll.
7. Hand the clip to `layer-video-timeline` for captions, the logo and the end card.

## Common mistakes

- Generating the clip first and cutting the line to fit it.
- Guessing the audio slot instead of reading it from `get_base_model`.
- Lip-syncing a wide shot, a profile, or a mouth covered by a hand or prop.
- A new voice on every line of the same character.
- Reporting a voice reference set as applied when `voice_applied` is absent.
- A line longer than the model's longest clip, sped up to fit.
- Scripting a generated presenter as a real customer's testimonial.

© layerai · MIT · layerai/skills

Similar skills

SKILL.md skills catalog →
roblox-characters gamedev-skills This Claude Code skill helps debug Roblox character scripts, animations, and movement. It applies when scripts fail after respawn, animations stop replicating, or sprint logic conflicts with Humanoid. CX Codex +1 9,300installs roblox-characters-animation EL4CTEO roblox-characters-animation — a Claude Code skill for Roblox characters and animation. It applies to work on movement, damage, respawns, avatars, weapons, and tweens. CX Codex +1 1,300installs talking-head-and-piece-to-camera social-media-skills talking-head-and-piece-to-camera is a Claude Code skill for preparing on-camera videos and coaching delivery. It handles setup questions, teleprompter formatting, retakes, and plans for filming several videos in one session. CX Codex +1 1,300installs runway-dev-characters runwayml runway-dev-characters — a skill for building Runway Characters integrations. Manage avatars, set up realtime Sessions, handle knowledge documents, and work with the Characters SDK and MCP tools. CX Codex +1 162installs talking-head-b-roll iart-ai talking-head-b-roll is a Claude Code skill that adds motion graphics and visual b-roll to talking-head footage, overlaying graphics or switching to full-frame scenes based on spoken words. CX Codex +1 871installs Word Counter — Words, Characters, Reading Time axel-belfort Word Counter — Words, Characters, Reading Time is an MCP server for Claude Code that counts words, characters, sentences, paragraphs, and reading time. It helps check text length limits. CX Codex +1 2,524installs

From the same set33

The whole set →
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 layer-video-looks layer-video-looks — a Claude Code skill for styling, grading, and keying video items on the Layer timeline. Operates during clip post-processing to unify mismatched shots or add retro and film filters. CX Codex +1 1,100installs layer-video-fixes The layer-video-fixes Claude Code skill repairs specific defects in Layer video clips instead of generating them again. It handles requests to extend a shot, replace a subject, change lighting, or improve image quality. CX Codex +1 1,100installs layer-video-continuity The layer-video-continuity skill for Claude Code maintains visual continuity across multi-shot Layer video generations. It carries characters, lighting, and action across cutscenes or trailers. CX Codex +1 1,100installs layer-video-direction layer-video-direction — a skill for Claude Code directs camera motion, lenses, framing, and pacing for single video shots on Layer. Runs when choreographing shot generation or resolving camera drift. CX Codex +1 1,100installs layer-environments The layer-environments Claude Code skill creates game backgrounds, parallax layers, 360° panoramas, and worlds with Layer. It runs for environment art, looping or aligning layers, and exports to Godot or Unity. CX Codex +1 1,100installs layer-vfx layer-vfx — a skill for Claude Code designs game visual effects and compiles them into sprite sheets. Generates isolated spell bursts, explosions, or loops and unpacks video clips into engine-ready flipbooks. CX Codex +1 1,100installs layer-tilesets The layer-tilesets Claude Code skill builds game tiles on a shared grid. It activates for isometric, hex, and top-down tilesets, including buildings shown from several sides. CX Codex +1 1,100installs

Project sponsors

Companies that keep this analytics open