# NVIDIA Kimodo Text to Motion — API Reference

Model ID: `model_nvidia-kimodo-text-to-motion`

---

## Authentication

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=api_keys) under API Keys.
- Set them as environment variables `SCENARIO_SDK_API_KEY` and `SCENARIO_SDK_API_SECRET` — both SDKs pick them up by default.
- For raw HTTP (cURL), use Basic Auth: `Authorization: Basic base64("<API_KEY>:<API_SECRET>")`.

### Install the SDK

- JavaScript / TypeScript: `npm install @scenario-labs/sdk`
- Python: `pip install scenario-sdk`

---

## Generate

**Endpoint:** `POST https://api.cloud.scenario.com/v1/generate/custom/model_nvidia-kimodo-text-to-motion`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompts` | string[] | yes | - | The motions to generate, played in order with smooth transitions. Start each one with "A person..." and keep it to one or two actions. For example: "A person walks forward", then "A person sits down". |
| `durations` | number[] | - | `5` | How long each prompt's motion lasts, in seconds. Give a single value to use for all prompts, or one value per prompt. |
| `constraints` | assetId | - | - | Optional JSON file of Kimodo constraints: full-body keyframes, hand or foot positions, or a ground path for the character to follow. Set each constraint at a frame number, counted from the start of the whole sequence at 30 frames per second. Positions are Y-up, in meters, relative to where the motion starts. |
| `numOutputs` | number | - | `1` | How many alternative motions to generate for the same prompts. |
| `numInferenceSteps` | number | - | `100` | Number of denoising steps. Fewer steps are faster; more steps give higher quality. |
| `guidanceScale` | number | - | `2` | How closely the motion follows your prompts. |
| `guidanceType` | string | - | `separated` | None (`nocfg`) turns guidance off, Regular (`regular`) applies the guidance scale, and Separated (`separated`) applies the guidance scale to the prompts and the constraint guidance scale to the constraints. |
| `constraintGuidanceScale` | number | - | `2` | How closely the motion follows your constraints. Used in Separated guidance mode only. |
| `numTransitionFrames` | number | - | `5` | Number of frames used to blend one prompt's motion into the next. |
| `firstHeadingAngle` | number | - | `0` | The direction the character faces at the start, in radians around the vertical (Y) axis. 0 faces +Z. |
| `postProcessing` | boolean | - | `true` | Reduces foot sliding and snaps the motion onto your constraints. |
| `seed` | number | - | - | Used to reproduce previous results |
| `bvhStandardTPose` | boolean | - | `false` | Writes the BVH with a standard T-pose as its rest pose, instead of the skeleton's default rest pose. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_nvidia-kimodo-text-to-motion" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompts": [],
  "durations": [
    5
  ],
  "numOutputs": 1,
  "numInferenceSteps": 100,
  "guidanceScale": 2,
  "guidanceType": "separated",
  "constraintGuidanceScale": 2,
  "numTransitionFrames": 5,
  "firstHeadingAngle": 0,
  "postProcessing": true,
  "bvhStandardTPose": false
}
EOF
```

**Python**

```python
import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),
)

body = {
    "prompts": [],
    "durations": [
        5
    ],
    "numOutputs": 1,
    "numInferenceSteps": 100,
    "guidanceScale": 2,
    "guidanceType": "separated",
    "constraintGuidanceScale": 2,
    "numTransitionFrames": 5,
    "firstHeadingAngle": 0,
    "postProcessing": True,
    "bvhStandardTPose": False
}

response = client.generate.run_model(
    model_id="model_nvidia-kimodo-text-to-motion",
    body=body,
)
print(response)
```

**JavaScript**

```javascript
import Scenario from "@scenario-labs/sdk";

const client = new Scenario({
  apiKey: process.env["SCENARIO_SDK_API_KEY"],
  apiSecret: process.env["SCENARIO_SDK_API_SECRET"],
});

const body = {
  "prompts": [],
  "durations": [
    5
  ],
  "numOutputs": 1,
  "numInferenceSteps": 100,
  "guidanceScale": 2,
  "guidanceType": "separated",
  "constraintGuidanceScale": 2,
  "numTransitionFrames": 5,
  "firstHeadingAngle": 0,
  "postProcessing": true,
  "bvhStandardTPose": false
};

const response = await client.generate.runModel("model_nvidia-kimodo-text-to-motion", { body });
console.info(response);
```

---

## Retrieve Results

After submitting a generation request, you receive a `jobId`. Poll the job until `job.status` is `"success"`. The generated asset IDs are in `job.metadata.assetIds`.

**Endpoint:** `GET https://api.cloud.scenario.com/v1/jobs/{jobId}`

### Example Requests

**cURL**

```bash
curl -X GET "https://api.cloud.scenario.com/v1/jobs/<JOB_ID>" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)"
```

**Python**

```python
job = client.jobs.retrieve(job_id="<JOB_ID>")
print(job.status)
print(job.metadata.asset_ids)
```

**JavaScript**

```javascript
// Option 1 — wait on the response from runModel using the SDK helper
const completed = await response.job.wait();
console.info(completed.status);
console.info(completed.metadata?.assetIds);

// Option 2 — retrieve a job by its ID
const job = await client.jobs.retrieve("<JOB_ID>");
console.info(job.status);
console.info(job.metadata?.assetIds);
```

**Example response:**

```json
{
  "job": {
    "jobId": "job_abc123",
    "status": "success",
    "metadata": {
      "assetIds": [
        "asset_abc123"
      ]
    }
  }
}
```

> **Important:** Generated asset URLs are **temporary** and expire after a short period. Download and store any images you wish to keep before the URL expires. More info: [Content Delivery Network (CDN)](https://docs.scenario.com/get-started/documentation/content-delivery-network-cdn).

---

*Generated by [Scenario](https://app.scenario.com)*