Bring your own audio: lip-sync a face (an R2-hosted image / character sheet, OR an existing clip) to a provided audio track. No text-to-speech or voice cloning — the character speaks your uploaded recording. Output is a 9:16 talking-head video.
When to use this
Call this skill when the user asks for the outcome described above. It runs on the agent-media vNext primitive runtime via the mcp__agent-media__make_lip_sync MCP tool. Authentication is the user's existing agent-media Bearer token (issued by agent-media login).
How to call it
Preferred path: MCP tool mcp__agent-media__make_lip_sync. Schema is auto-published via tools/list against the same MCP server, so don't restate the schema here — trust the server's response.
Fallback path: REST.
POST https://api.agent-media.ai/v1/skills/make_lip_sync/run
Authorization: Bearer $AGENT_MEDIA_API_KEY
Content-Type: application/json
Idempotency-Key: <any unique string per intent>
{ "image_url": "https://pub-...r2.dev/vnext/primitive-runs//character-sheet.png", "audio_url": "https://pub-...r2.dev/vnext/.mp3", "duration": 10, "aspect_ratio": "9:16" }
## What it costs and how long it takes
- Credits: `140/280/420 (5s/10s/15s)`
- Wall time (typical): `420–480s`
- Deducted at submit; refunded on terminal failure.
## Polling the result
```http
GET https://api.agent-media.ai/v1/primitives/runs/<run_id>
Authorization: Bearer $AGENT_MEDIA_API_KEY
House rules baked into this skill
- See reference/realism-rubric.md for the realism doctrine baked into every prompt.
- See reference/auth.md for first-time install and
agent-media login.
Source of truth
This file is auto-generated by scripts/generate-public-skill.ts from the registry at services/api-v2/src/skills/registry.ts. Do not hand-edit; CI rejects drift.