---
title: "Generate text-driven skeletal animations for an already-rigged 3D model. Pass the rigged GLB in `model` (URL or base64) and a motion `prompt` (e.g. \"walking\", \"swinging its axe\"). The model must already have a skeleton - rig it first via the rig endpoint if not. Synchronous until September 10, 2026: returns num_variants candidate animations (default 4), each a standalone animation-only GLB (skeleton + one clip, no mesh) in `glb_url` plus an mp4 `preview_url`, so you can pick the best one and fuse it with your model in a game engine or three.js. mode selects the representation - rot_trans (default, most faithful) or rot_only (for retargeting). Animation quality is hit-or-miss, which is why multiple candidates are returned. Credits are charged once per call regardless of variant count, only on success. Requires an API key (user scope). Async is the intended integration pattern: pass `async: true` and the call returns 202 with a job id - poll `GET /assets/jobs/{id}` (`getApiJob` in MCP), honouring poll_after_ms or long-polling with wait=30, until status is succeeded, whose result field is exactly the response documented for this operation. Synchronous responses are deprecated: they remain the default until September 10, 2026, after which requests default to async and return 202 with a job id; set `async: false` explicitly to keep synchronous behavior during and after the transition. Synchronous calls run on the same queue: the response carries an X-Ludo-Job-Id header, and a job still running after 15 minutes comes back as 202 with the job instead of an error. Each account may have up to 50 generations queued or running at once via the API; a request beyond that returns 429 (code PENDING_JOBS_LIMIT)."
method: POST
path: "/assets/3d-model/animate"
tags: ["3D Models"]
---

# Generate text-driven skeletal animations for an already-rigged 3D model. Pass the rigged GLB in \`model\` (URL or base64) and a motion \`prompt\` (e.g. "walking", "swinging its axe"). The model must already have a skeleton - rig it first via the rig endpoint if not. Synchronous until September 10, 2026: returns num_variants candidate animations (default 4), each a standalone animation-only GLB (skeleton + one clip, no mesh) in \`glb_url\` plus an mp4 \`preview_url\`, so you can pick the best one and fuse it with your model in a game engine or three.js. mode selects the representation - rot_trans (default, most faithful) or rot_only (for retargeting). Animation quality is hit-or-miss, which is why multiple candidates are returned. Credits are charged once per call regardless of variant count, only on success. Requires an API key (user scope). Async is the intended integration pattern: pass \`async: true\` and the call returns 202 with a job id - poll \`GET /assets/jobs/{id}\` (\`getApiJob\` in MCP), honouring poll_after_ms or long-polling with wait=30, until status is succeeded, whose result field is exactly the response documented for this operation. Synchronous responses are deprecated: they remain the default until September 10, 2026, after which requests default to async and return 202 with a job id; set \`async: false\` explicitly to keep synchronous behavior during and after the transition. Synchronous calls run on the same queue: the response carries an X-Ludo-Job-Id header, and a job still running after 15 minutes comes back as 202 with the job instead of an error. Each account may have up to 50 generations queued or running at once via the API; a request beyond that returns 429 (code PENDING_JOBS_LIMIT).

`POST /assets/3d-model/animate`

## Request body

- Animate3DModelPayload
  - `model` string, required — URL or base64-encoded already-rigged GLB to animate. Rig it first via the rig endpoint if it has no skeleton.
  - `prompt` string, required — Desired motion, e.g. "walking" or "swinging its axe".
  - `mode` 'rot_trans' | 'rot_only' — Animation representation: rot_trans (per-bone rotation+translation, most faithful) or rot_only (rotation + root translation only, for retargeting).
  - `num_variants` integer — Number of candidate animations to generate; each returned as a standalone animation-only GLB with an mp4 preview.
  - `loop` boolean — Return to the initial pose: each clip plays forward then mirrors back to the rest pose for a seamless loop. Best for one-way motions (crouch, punch, wave); reads oddly for cyclic gaits like walking.
  - `augment_prompt` boolean — Rewrite the prompt into a detailed motion caption with an LLM (recommended).
  - `request_id` string — Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable with the results endpoint.
  - `async` boolean — When true, return 202 immediately with a job id instead of waiting for the result. Poll GET /assets/jobs/{id}. Defaults to false (synchronous).

## Response `200`

Success

- AnimationCandidates
  - `animations` AnimationClip[]
    - `clip_name` string
    - `prompt` string
    - `preset_id` string — Set when the clip came from the preset library (retargeting) rather than a text prompt.
    - `mode` 'rot_trans' | 'rot_only'
    - `seed` integer
    - `glb_url` string
    - `preview_url` string
    - `motion` number, float
    - `fit_rmse` number, float

## Other responses

- `202` — Accepted - the generation was queued (async: true, or a synchronous call still running after 15 minutes). Poll GET /assets/jobs/{id}.
- `400` — Error

## Changes

- **2026-08-30** `a8a0b85d1839` — 1 info
  - added the success response with the status `202`

[Change history](https://skmtc.dev/ludo/apis/ludo-ai-api/changes/assets/3d-model/animate/post.md)

---

[API](https://skmtc.dev/ludo/apis/ludo-ai-api.md) · [All operations](https://skmtc.dev/ludo/apis/ludo-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/ludo/ludo-ai-api/revisions/37a21589e770/schema)