### Example Avatar Response

Source: https://docs.dev.runwayml.com/api/#tag/Start-generating/paths/~1v1~1image_to_video/post

This is an example of a successful response when creating an avatar, showing the structure of the returned avatar object.

```json
{
  * "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
  * "name": "string",
  * "personality": "string",
  * "startScript": "string",
  * "voice": {
    * "type": "runway-live-preset",
    * "presetId": "victoria",
    * "name": "string",
    * "description": "string"
},
  * "referenceImageUri": "string",
  * "processedImageUri": "string",
  * "documentIds": [
    * "497f6eca-6276-4993-bfeb-53cbbbba6f08"
],
  * "createdAt": "2019-08-24T14:15:22Z",
  * "updatedAt": "2019-08-24T14:15:22Z",
  * "status": "AvatarProcessing"

}
```

--------------------------------

### POST /v1/image_to_video

Source: https://docs.dev.runwayml.com/api

Starts a new task to generate a video from an image.

```APIDOC
## POST /v1/image_to_video

### Description
This endpoint will start a new task to generate a video from an image.

### Method
POST

### Endpoint
/v1/image_to_video

### Authentication
Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. This field must be set to the exact value `2024-11-06`.

### Request Body
- **model** (string) - Required - Accepted values: "gen4.5", "gen4_turbo", "gen3a_turbo", "veo3.1", "veo3.1_fast", "veo3".
- **promptText** (string) - Required - A non-empty string up to 1000 characters describing the desired output.
- **promptImage** (string or Array of PromptImages) - Required - A HTTPS URL, Runway or data URI containing an encoded image, or an array of PromptImages.
  - **PromptImages** (Array of objects) - Required - An array containing at least one PromptImage object.
    - **uri** (string) - Required - A HTTPS URL, Runway or data URI containing an encoded image.
    - **position** (string) - Required - The position of the image in the output video. Must be set to the exact value `first`.
    - **ratio** (string) - Required - The resolution of the output video. Accepted values: "1280:720", "720:1280", "1104:832", "960:960", "832:1104", "1584:672".
- **duration** (integer) - Required - The number of seconds of duration for the output video. Must be an integer from 2 to 10.
- **seed** (integer) - Optional - If unspecified, a random number is chosen. Varying the seed integer is a way to get different results for the same other request parameters. Using the same seed integer for an identical request will produce similar results.
- **contentModeration** (object) - Optional - Settings that affect the behavior of the content moderation system.
  - **publicFigureThreshold** (string) - Optional - Accepted values: "auto", "low". When set to `low`, the content moderation system will be less strict about preventing generations that include recognizable public figures.

### Request Example
```json
{
  "model": "gen4_turbo",
  "promptImage": "https://example.com/bunny.jpg",
  "promptText": "A cute bunny hopping in a meadow",
  "duration": 10
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the created task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```

#### Error Response (429)
- You have exceeded the rate limit for this endpoint.
```

--------------------------------

### POST /v1/text_to_video

Source: https://docs.dev.runwayml.com/api

Starts a new task to generate a video from a text prompt.

```APIDOC
## POST /v1/text_to_video

### Description
This endpoint will start a new task to generate a video from a text prompt.

### Method
POST

### Endpoint
/v1/text_to_video

### Authentication
Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. This field must be set to the exact value `2024-11-06`.
```

--------------------------------

### Generate Avatar Video using Node.js SDK

Source: https://docs.dev.runwayml.com/api

Initiates an asynchronous task to generate an avatar video. This example uses text-to-speech with a preset voice. Poll the task ID for completion and retrieve the video URL. Ensure the SDK is installed and the API secret is set as an environment variable.

```javascript
// npm install --save @runwayml/sdk
import RunwayML from '@runwayml/sdk';

// The env var RUNWAYML_API_SECRET is expected to contain your API key.
const client = new RunwayML();

const task = await client.avatarVideos
  .create({
    model: 'gwm1_avatars',
    avatar: {
      type: 'runway-preset',
      presetId: 'influencer',
    },
    speech: {
      type: 'text',
      text: 'Welcome to Runway! I can help you create amazing videos.',
      voice: { type: 'preset', presetId: 'clara' },
    },
  })
  .waitForTaskOutput();

console.log(task);
```

--------------------------------

### Use promptImage with a single image object at the beginning

Source: https://docs.dev.runwayml.com/api-details/versions/2024-11-06

Example of using the `promptImage` parameter with an image object, specifying its position as 'first'.

```json
{
  "promptImage": [
    {
      "uri": "https://example.com/image.jpg",
      "position": "first"
    }
  ]
}
```

--------------------------------

### POST /v1/sound_effect

Source: https://docs.dev.runwayml.com/api

Starts a new task to generate sound effects from a text description.

```APIDOC
## POST /v1/sound_effect

### Description
This endpoint will start a new task to generate sound effects from a text description.

### Method
POST

### Endpoint
/v1/sound_effect

### Authentication
- **Authorization** - Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. This field must be set to the exact value `2024-11-06`.
```

--------------------------------

### Use promptImage with multiple image objects

Source: https://docs.dev.runwayml.com/api-details/versions/2024-11-06

Example of using the `promptImage` parameter with two image objects, one at the 'first' position and another at the 'last' position.

```json
{
  "promptImage": [
    {
      "uri": "https://example.com/image1.jpg",
      "position": "first"
    },
    {
      "uri": "https://example.com/image2.jpg",
      "position": "last"
    }
  ]
}
```

--------------------------------

### Generate Avatar Video

Source: https://docs.dev.runwayml.com/api

Starts an asynchronous task to generate a video of an avatar speaking. Poll GET /v1/tasks/:id to check progress and retrieve the output video URL once complete.

```APIDOC
## POST /v1/avatar_videos

### Description
Generate avatar video from audio or text.

### Method
POST

### Endpoint
/v1/avatar_videos

### Authentication
Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. This field must be set to the exact value `2024-11-06`.

### Request Body
- **model** (string) - Required - The model to use for avatar video generation. This field must be set to the exact value `gwm1_avatars`.
- **avatar** (RunwayPresetAvatar or CustomAvatar) - Required - The avatar configuration for the session.
  - **RunwayPresetAvatar** (object)
    - **type** (string) - Required - This field must be set to the exact value `runway-preset`.
    - **presetId** (string) - Required - Accepted values:"game-character", "music-superstar", "game-character-man", "cat-character", "influencer", "tennis-coach", "human-resource", "fashion-designer", "cooking-teacher" - ID of a preset avatar.
  - **CustomAvatar** (object)
    - **type** (string) - Required - This field must be set to the exact value `custom`.
    - **avatarId** (string) - Required - ID of a user-created avatar.
- **speech** (AudioInput or TextInput) - Required - The speech source for avatar video generation. Either an audio file or text script.
  - **AudioInput** (object)
    - **type** (string) - Required - This field must be set to the exact value `audio`.
    - **audio** (string) - Required - A HTTPS URL, Runway or data URI containing an encoded audio.
  - **TextInput** (object)
    - **type** (string) - Required - This field must be set to the exact value `text`.
    - **text** (string) - Required - Text script for speech-driven video generation.
    - **voice** (RunwayPresetVoice or CustomVoice) - Optional - Voice override for TTS.
      - **RunwayPresetVoice** (object)
        - **type** (string) - Required - This field must be set to the exact value `preset`.
        - **presetId** (string) - Required - Accepted values:"victoria", "vincent", "clara", "drew", "skye", "max", "morgan", "felix", "mia", "marcus", "summer", "ruby", "aurora", "jasper", "leo", "adrian", "nina", "emma", "blake", "david", "maya", "nathan", "sam", "georgia", "petra", "adam", "zach", "violet", "roman", "luna".
      - **CustomVoice** (object)
        - **type** (string) - Required - This field must be set to the exact value `custom`.
        - **id** (string) - Required - ID of a custom voice.

### Responses
#### Success Response (200)
- **id** (string) - The ID of the generated task.

### Request Example
```json
{
  "model": "gwm1_avatars",
  "avatar": {
    "type": "runway-preset",
    "presetId": "influencer"
  },
  "speech": {
    "type": "text",
    "text": "Welcome to Runway! I can help you create amazing videos.",
    "voice": {
      "type": "preset",
      "presetId": "clara"
    }
  }
}
```
```

--------------------------------

### POST /v1/character_performances

Source: https://docs.dev.runwayml.com/api

Starts a new task to generate a character performance based on provided character and reference media.

```APIDOC
## POST /v1/character_performances

### Description
This endpoint starts a new task to generate a character performance. You can provide a character image or video and a reference video for the performance.

### Method
POST

### Endpoint
/v1/character_performances

### Parameters
#### Request Body
- **model** (string) - Required - This field must be set to the exact value `act_two`.
- **character** (object) - Required - The character to control. Can be `CharacterImage` or `CharacterVideo`.
  - **type** (string) - Required - Must be `image` or `video`.
  - **uri** (string) - Required - A HTTPS URL, Runway upload URI, or data URI for the character media.
- **reference** (object) - Required - The reference video containing the performance to apply to the character (`CharacterReferenceVideo`).
  - **type** (string) - Required - Must be `video`.
  - **uri** (string) - Required - A HTTPS URL, Runway upload URI, or data URI for the reference video.
- **seed** (integer) - Optional - An integer between 0 and 4294967295. Used to generate reproducible results.
- **bodyControl** (boolean) - Optional - A boolean indicating whether to enable body control.
- **expressionIntensity** (integer) - Optional - An integer between 1 and 5. Default: 3. Increases the intensity of the character's expression.
- **ratio** (string) - Optional - The resolution of the output video. Accepted values: "1280:720", "720:1280", "960:960", "1104:832", "832:1104", "1584:672".
- **contentModeration** (object) - Optional - Settings that affect the behavior of the content moderation system.
  - **publicFigureThreshold** (string) - Optional - Accepted values: "auto", "low". Less strict about recognizable public figures when set to `low`.

### Request Example
```json
{
  "model": "act_two",
  "character": {
    "type": "video",
    "uri": "https://example.com/posedCharacter.mp4"
  },
  "reference": {
    "type": "video",
    "uri": "https://example.com/actorPerformance.mp4"
  },
  "ratio": "1280:720"
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the created task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```

### Error Handling
- **429** - You have exceeded the rate limit for this endpoint.
```

--------------------------------

### Use promptImage with a single string URI

Source: https://docs.dev.runwayml.com/api-details/versions/2024-11-06

Example of using the `promptImage` parameter with a single image URI string.

```json
{
  "promptImage": "https://example.com/image.jpg"
}
```

--------------------------------

### Use promptImage with a single image object at the end

Source: https://docs.dev.runwayml.com/api-details/versions/2024-11-06

Example of using the `promptImage` parameter with an image object, specifying its position as 'last'. This will make the video end with the image.

```json
{
  "promptImage": [
    {
      "uri": "https://example.com/image.jpg",
      "position": "last"
    }
  ]
}
```

--------------------------------

### Run a Published Workflow

Source: https://docs.dev.runwayml.com/api

Starts a new task to execute a published workflow.

```APIDOC
## POST /v1/workflows/{id}

### Description
Starts a new task to execute a published workflow. You can optionally provide custom input values via `nodeOutputs` to override the defaults defined in the workflow graph.

### Method
POST

### Endpoint
/v1/workflows/{id}

### Headers
- **Authorization** (string) - Required - Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.

### Path Parameters
- **id** (string) - Required - The ID of the published workflow to run. You can copy this value from the developer portal.

### Request Body
(Optional) - `nodeOutputs`: An object where keys are node IDs and values are the custom inputs for those nodes.
```

--------------------------------

### Get Organization Information

Source: https://docs.dev.runwayml.com/api

Retrieves usage tier and credit balance for the organization.

```APIDOC
## Get Organization Information

### Description
Get usage tier and credit balance information about the organization associated with the API key used to make the request.

### Method
GET

### Endpoint
/v1/organization

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.
- **Authorization** (string) - Required - Bearer token for authentication.

### Responses
#### Success Response (200)
- **tier** (object) - Information about the organization's tier.
  - **maxMonthlyCreditSpend** (number)
  - **models** (object) - Details on model limits.
    - **[model_name]** (object)
      - **maxConcurrentGenerations** (number)
      - **maxDailyGenerations** (number)
- **creditBalance** (number) - The current credit balance.
- **usage** (object) - Current usage statistics.
  - **models** (object)
    - **[model_name]** (object)
      - **dailyGenerations** (number)

#### Response Example
```json
{
  "tier": {
    "maxMonthlyCreditSpend": 9007199254740991,
    "models": {
      "property1": {
        "maxConcurrentGenerations": 9007199254740991,
        "maxDailyGenerations": 9007199254740991
      },
      "property2": {
        "maxConcurrentGenerations": 9007199254740991,
        "maxDailyGenerations": 9007199254740991
      }
    }
  },
  "creditBalance": 9007199254740991,
  "usage": {
    "models": {
      "property1": {
        "dailyGenerations": 9007199254740991
      },
      "property2": {
        "dailyGenerations": 9007199254740991
      }
    }
  }
}
```
```

--------------------------------

### Video to Video Generation API

Source: https://docs.dev.runwayml.com/api

This endpoint starts a new task to generate a video based on an input video and a prompt.

```APIDOC
## Video to Video Generation

### Description
This endpoint will start a new task to generate a video based on an input video and a prompt.

### Method
POST

### Endpoint
/v1/video_to_video

### Request Body
- **model** (string) - Required - Accepted values: "gen4_aleph"
- **videoUri** (string) - Required - The URI of the input video.
- **promptText** (string) - Required - A description of the desired output video.
- **references** (array of objects) - Required - An array of reference objects, each containing a `type` and `uri`.
  - **type** (string) - Required - Accepted values: "image"
  - **uri** (string) - Required - The URI of the reference image.
- **ratio** (string) - Required - The desired aspect ratio for the output video (e.g., "1280:720").

### Request Example
```json
{
  "model": "gen4_aleph",
  "videoUri": "https://example.com/bunny.mp4",
  "promptText": "string",
  "references": [
    {
      "type": "image",
      "uri": "https://example.com/easter-scene.jpg"
    }
  ],
  "ratio": "1280:720"
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the created task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```
```

--------------------------------

### Speech to Speech API

Source: https://docs.dev.runwayml.com/api

This endpoint starts a new task to generate speech from audio.

```APIDOC
## Speech to Speech API

### Description
This endpoint starts a new task to generate speech from audio.

### Method
POST

### Endpoint
/v1/speech_to_speech

### Request Body
- **model** (string) - Required - This field must be set to the exact value `eleven_multilingual_sts_v2`.
- **media** (object) - Required - The media to process.
  - **type** (string) - Required - Must be `audio` or `video`.
  - **uri** (string) - Required - A HTTPS URL to the audio or video file.
- **voice** (object) - Required - The voice to use for the generated speech.
  - **type** (string) - Required - Must be `runway-preset`.
  - **presetId** (string) - Required - The preset voice ID to use for the generated speech. Accepted values: "Maggie", "Noah", etc.

### Request Example
```json
{
  "model": "eleven_multilingual_sts_v2",
  "media": {
    "type": "audio",
    "uri": "https://example.com/audio.mp3"
  },
  "voice": {
    "type": "runway-preset",
    "presetId": "Maggie"
  }
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the created task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```
```

--------------------------------

### Speech to Speech API

Source: https://docs.dev.runwayml.com/api/#tag/Start-generating/paths/~1v1~1image_to_video/post

This endpoint starts a new task to generate speech from audio or video input.

```APIDOC
## Speech to Speech API

### Description
This endpoint starts a new task to generate speech from audio or video input.

### Method
POST

### Endpoint
/v1/speech_to_speech

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.
- **Authorization** (string) - Required - Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Request Body
- **model** (string) - Required - Must be set to the exact value `eleven_multilingual_sts_v2`.
- **media** (object) - Required - The input media for speech generation.
  - **type** (string) - Required - Must be set to `audio` or `video`.
  - **uri** (string) - Required - A HTTPS URL to the audio or video file.
- **voice** (object) - Required - The voice to use for the generated speech.
  - **type** (string) - Required - Must be set to `runway-preset`.
  - **presetId** (string) - Required - The preset voice ID to use (e.g., "Maggie", "Noah").

### Request Example
```json
{
  "model": "eleven_multilingual_sts_v2",
  "media": {
    "type": "audio",
    "uri": "https://example.com/audio.mp3"
  },
  "voice": {
    "type": "runway-preset",
    "presetId": "Maggie"
  }
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the created task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```

#### Error Response (429)
- **message** (string) - You have exceeded the rate limit for this endpoint.
```

--------------------------------

### Generate Video from Image using Node.js SDK

Source: https://docs.dev.runwayml.com/api

Use the Node.js SDK to start a new task for generating a video from an image. Ensure the RUNWAYML_API_SECRET environment variable is set with your API key. The .waitForTaskOutput() method waits for the generation to complete.

```javascript
// npm install --save @runwayml/sdk
import RunwayML from '@runwayml/sdk';

// The env var RUNWAYML_API_SECRET is expected to contain your API key.
const client = new RunwayML();

const task = await client.imageToVideo
  .create({
    model: 'gen4_turbo',
    promptImage: 'https://example.com/bunny.jpg',
    promptText: 'A cute bunny hopping in a meadow',
    duration: 10,
  })
  .waitForTaskOutput();

console.log(task);
```

--------------------------------

### Text to Speech API

Source: https://docs.dev.runwayml.com/api

This endpoint will start a new task to generate speech from text.

```APIDOC
## Text to Speech API

### Description
This endpoint will start a new task to generate speech from text.

### Method
POST

### Endpoint
/v1/text_to_speech

### Authentication
`Authorization`: Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.

### Request Body
- **model** (string) - Required - This field must be set to the exact value `eleven_multilingual_v2`.
- **promptText** (string) - Required - A non-empty string up to 1000 characters describing the desired speech.
- **voice** (object) - Required - The voice to use for the generated speech.
  - **type** (string) - Required - Must be `runway-preset`.
  - **presetId** (string) - Required - The preset voice ID. Accepted values: "Maya", "Arjun", "Serene", "Bernard", "Billy", "Mark", "Clint", "Mabel", "Chad", "Leslie", "Eleanor", "Elias", "Elliot", "Grungle", "Brodie", "Sandra", "Kirk", "Kylie", "Lara", "Lisa", "Malachi", "Marlene", "Martin", "Miriam", "Monster", "Paula", "Pip", "Rusty", "Ragnar", "Xylar", "Maggie", "Jack", "Katie", "Noah", "James", "Rina", "Ella", "Mariah", "Frank", "Claudia", "Niki", "Vincent", "Kendrick", "Myrna", "Tom", "Wanda", "Benjamin", "Kiana", "Rachel".

### Request Example
```json
{
  "model": "eleven_multilingual_v2",
  "promptText": "The quick brown fox jumps over the lazy dog",
  "voice": {
    "type": "runway-preset",
    "presetId": "Leslie"
  }
}
```

### Response
#### Success Response (200)
- **id** (string) - The ID of the created task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```
```

--------------------------------

### Generate Avatar Video

Source: https://docs.dev.runwayml.com/api/#tag/Start-generating/paths/~1v1~1image_to_video/post

Starts an asynchronous task to generate a video of an avatar speaking. You can provide speech as either an audio file or text for Text-to-Speech (TTS). Progress can be monitored by polling the GET /v1/tasks/:id endpoint.

```APIDOC
## POST /v1/avatar_videos

### Description
Generate avatar video from audio or text. Start an asynchronous task to generate a video of an avatar speaking. Provide `speech` with `type: "audio"` (audio file) or `type: "text"` (text script for TTS). Poll `GET /v1/tasks/:id` to check progress and retrieve the output video URL once complete.

### Method
POST

### Endpoint
/v1/avatar_videos

### Authentication
Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.

### Request Body
- **model** (string) - Required - The model to use for avatar video generation. Must be set to `gwm1_avatars`.
- **avatar** (RunwayPresetAvatar or CustomAvatar) - Required - The avatar configuration.
  - **RunwayPresetAvatar** (object)
    - **type** (string) - Required - Must be `runway-preset`.
    - **presetId** (string) - Required - Accepted values: `game-character`, `music-superstar`, `game-character-man`, `cat-character`, `influencer`, `tennis-coach`, `human-resource`, `fashion-designer`, `cooking-teacher`.
  - **CustomAvatar** (object)
    - **type** (string) - Required - Must be `custom`.
    - **avatarId** (string) - Required - ID of a user-created avatar.
- **speech** (AudioInput or TextInput) - Required - The speech source.
  - **AudioInput** (object)
    - **type** (string) - Required - Must be `audio`.
    - **audio** (string) - Required - A HTTPS URL, Runway, or data URI containing encoded audio.
  - **TextInput** (object)
    - **type** (string) - Required - Must be `text`.
    - **text** (string) - Required - Text script for speech-driven video generation (1-1000 characters).
- **voice** (RunwayPresetVoice or CustomVoice) - Optional - Voice override for TTS.
  - **RunwayPresetVoice** (object)
    - **type** (string) - Required - Must be `preset`.
    - **presetId** (string) - Required - Accepted values: `victoria`, `vincent`, `clara`, `drew`, `skye`, `max`, `morgan`, `felix`, `mia`, `marcus`, `summer`, `ruby`, `aurora`, `jasper`, `leo`, `adrian`, `nina`, `emma`, `blake`, `david`, `maya`, `nathan`, `sam`, `georgia`, `petra`, `adam`, `zach`, `violet`, `roman`, `luna`.
  - **CustomVoice** (object)
    - **type** (string) - Required - Must be `custom`.
    - **id** (string) - Required - ID of a custom voice.

### Request Example
```javascript
// npm install --save @runwayml/sdk
import RunwayML from '@runwayml/sdk';

// The env var RUNWAYML_API_SECRET is expected to contain your API key.
const client = new RunwayML();

const task = await client.avatarVideos
  .create({
    model: 'gwm1_avatars',
    avatar: {
      type: 'runway-preset',
      presetId: 'influencer',
    },
    speech: {
      type: 'text',
      text: 'Welcome to Runway! I can help you create amazing videos.',
      voice: { type: 'preset', presetId: 'clara' },
    },
  })
  .waitForTaskOutput();

console.log(task);
```

### Responses
#### Success Response (200)
- **id** (string) - The ID of the generated task.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```
```

--------------------------------

### Upload File and Create Video Generation Task with Node.js SDK

Source: https://docs.dev.runwayml.com/api

This snippet demonstrates uploading a media file and then using the returned URI to create a video generation task. Ensure the RUNWAYML_API_SECRET environment variable is set.

```javascript
// npm install --save @runwayml/sdk
import RunwayML from '@runwayml/sdk';
import fs from 'node:fs';

// The env var RUNWAYML_API_SECRET is expected to contain your API key.
const client = new RunwayML();

filename = './funny-cats.mp4';
const uploadUri = await client.uploads.createEphemeral(
  fs.createReadStream(filename),
);

// Use the runwayUri in generation requests
const task = await client.videoToVideo
  .create({
    model: 'gen4_aleph',
    videoUri: uploadUri,
    promptText: 'Add the easter elements to the cat video',
    references: [
      {
        type: 'image',
        uri: 'https://example.com/easter-scene.jpg',
      },
    ],
    ratio: '1280:720',
  })
  .waitForTaskOutput();

console.log(task);
```

--------------------------------

### Get Avatar

Source: https://docs.dev.runwayml.com/api

Retrieves details of a specific avatar.

```APIDOC
## Get Avatar
GET /v1/avatars/{id}

### Description
Get details of a specific avatar.

### Method
GET

### Endpoint
/v1/avatars/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The avatar ID.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.
- **Authorization** (string) - Required - Bearer token for authentication.

### Responses
#### Success Response (200)
- **id** (string) - The unique identifier for the avatar.
- **name** (string) - The name of the avatar.
- **personality** (string) - The personality traits of the avatar.
- **startScript** (string) - The initial script for the avatar.
- **voice** (object) - The voice configuration for the avatar.
  - **type** (string) - The type of voice (e.g., `runway-live-preset`).
  - **presetId** (string) - The ID of the voice preset.
  - **name** (string) - The name of the voice.
  - **description** (string) - A description of the voice.
- **referenceImageUri** (string) - The URI of the reference image for the avatar.
- **processedImageUri** (string) - The URI of the processed avatar image.
- **documentIds** (array) - List of document IDs associated with the avatar.
- **createdAt** (string) - The timestamp when the avatar was created.
- **updatedAt** (string) - The timestamp when the avatar was last updated.
- **status** (string) - The status of the avatar (e.g., `AvatarProcessing`).

### Request Example
```json
{
  "example": "request body"
}
```

### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
  "name": "string",
  "personality": "string",
  "startScript": "string",
  "voice": {
    "type": "runway-live-preset",
    "presetId": "victoria",
    "name": "string",
    "description": "string"
  },
  "referenceImageUri": "string",
  "processedImageUri": "string",
  "documentIds": [
    "497f6eca-6276-4993-bfeb-53cbbbba6f08"
  ],
  "createdAt": "2019-08-24T14:15:22Z",
  "updatedAt": "2019-08-24T14:15:22Z",
  "status": "AvatarProcessing"
}
```
```

--------------------------------

### Get Conversation

Source: https://docs.dev.runwayml.com/api

Retrieves detailed information about a specific conversation.

```APIDOC
## Get Conversation
GET /v1/avatars/{id}/conversations/{conversationId}

### Description
Get detailed information about a specific conversation, including the transcript and recording download URL when available. The conversation ID is the same value returned when the realtime session was created.

### Method
GET

### Endpoint
/v1/avatars/{id}/conversations/{conversationId}

### Parameters
#### Path Parameters
- **id** (string) - Required - The avatar ID.
- **conversationId** (string) - Required - The conversation ID. This is the same value as the realtime session ID for the call.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be set to `2024-11-06`.
- **Authorization** (string) - Required - Bearer token for authentication.

### Responses
#### Success Response (200)
- **id** (string) - The unique identifier for the conversation.
- **name** (string) - The name of the conversation.
- **avatar** (object) - Information about the avatar.
  - **type** (string) - The type of avatar (e.g., `preset`).
  - **presetId** (string) - The ID of the avatar preset.
- **createdAt** (string) - The timestamp when the conversation was created.
- **maxDuration** (number) - The maximum duration allowed for the conversation.
- **transcript** (array) - The conversation transcript.
  - **role** (string) - The role of the speaker (e.g., `user`).
  - **content** (string) - The content of the message.
  - **timestamp** (string) - The timestamp of the message.
  - **toolCalls** (array) - List of tool calls made during the conversation.
    - **id** (string) - The ID of the tool call.
    - **name** (string) - The name of the tool.
    - **arguments** (object) - The arguments passed to the tool.
  - **toolResults** (array) - Results of tool calls.
    - **id** (string) - The ID of the tool result.
    - **name** (string) - The name of the tool.
    - **result** (object) - The result of the tool call.
    - **error** (string) - Any error message associated with the tool result.
    - **durationMs** (number) - The duration of the tool execution in milliseconds.
- **recordingUrl** (string) - The URL to download the conversation recording.
- **tools** (array) - List of tools available for the conversation.
  - **type** (string) - The type of tool.
  - **name** (string) - The name of the tool.
  - **description** (string) - A description of the tool.
- **status** (string) - The status of the conversation (e.g., `Option 1`).
- **startedAt** (string) - The timestamp when the conversation started.
- **duration** (number) - The duration of the conversation.

### Request Example
```json
{
  "example": "request body"
}
```

### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
  "name": "string",
  "avatar": {
    "type": "preset",
    "presetId": "string"
  },
  "createdAt": "2019-08-24T14:15:22Z",
  "maxDuration": -9007199254740991,
  "transcript": [
    {
      "role": "user",
      "content": "string",
      "timestamp": "2019-08-24T14:15:22Z",
      "toolCalls": [
        {
          "id": "string",
          "name": "string",
          "arguments": {
            "property1": null,
            "property2": null
          }
        }
      ],
      "toolResults": [
        {
          "id": "string",
          "name": "string",
          "result": {
            "property1": null,
            "property2": null
          },
          "error": "string",
          "durationMs": 0
        }
      ]
    }
  ],
  "recordingUrl": "http://example.com",
  "tools": [
    {
      "type": "client_event",
      "name": "string",
      "description": "string"
    }
  ],
  "status": "Option 1",
  "startedAt": "2019-08-24T14:15:22Z",
  "duration": -9007199254740991
}
```
```

--------------------------------

### Create Realtime Session

Source: https://docs.dev.runwayml.com/api

This snippet demonstrates how to create a real-time session using the RunwayML SDK. It includes setting up the client and specifying model and avatar details.

```APIDOC
## POST /v1/realtime_sessions

### Description
Creates a new real-time session for avatar interactions.

### Method
POST

### Endpoint
/v1/realtime_sessions

### Request Body
- **model** (string) - Required - The model to use for the session.
- **avatar** (object) - Required - Details about the avatar.
  - **type** (string) - Required - The type of avatar ('custom').
  - **avatarId** (string) - Required - The ID of the custom avatar.

### Request Example
```json
{
  "model": "gwm1_avatars",
  "avatar": {
    "type": "custom",
    "avatarId": "550e8400-e29b-41d4-a716-446655440000"
  }
}
```

### Response
#### Success Response (200)
- **id** (string) - The unique identifier for the real-time session.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}
```
```

--------------------------------

### Get Document

Source: https://docs.dev.runwayml.com/api

Retrieves the details of a specific knowledge document by its ID.

```APIDOC
## GET /v1/documents/{id}

### Description
Gets details of a specific knowledge document.

### Authentication
- **Authorization** (string) - Required - Use the HTTP `Authorization` header with the `Bearer` scheme along with an API key.

### Path Parameters
- **id** (string) - Required - The unique identifier (UUID) of the document.

### Headers
- **X-Runway-Version** (string) - Required - The version of the RunwayML API being used. Must be `2024-11-06`.

### Responses
#### Success Response (200)
- **id** (string) - The unique identifier of the document.
- **name** (string) - The name of the document.
- **type** (string) - The type of the document (e.g., 'text').
- **usedBy** (array) - Information about entities using this document.
- **content** (string) - The content of the document.
- **createdAt** (string) - The timestamp when the document was created.
- **updatedAt** (string) - The timestamp when the document was last updated.

#### Response Example
```json
{
  "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
  "name": "Document Name",
  "type": "text",
  "usedBy": [
    {
      "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
      "name": "Example Service",
      "imageUrl": "http://example.com"
    }
  ],
  "content": "# Document Content...",
  "createdAt": "2019-08-24T14:15:22Z",
  "updatedAt": "2019-08-24T14:15:22Z"
}
```
```