asset.add

{
  "event_id": "evt_asset_add_001",
  "type": "asset.add",
  "assets": {
    "images": [
      {
        "asset_id": "OBJ_0",
        "url": "https://YOUR_CDN.example/speaker.png",
        "mime_type": "image/png",
        "description": "A dark gray cylindrical speaker<OBJ_0> with a perforated grille and a flat base"
      }
    ],
    "audio": [
      {
        "asset_id": "promo_sting",
        "url": "https://cdn.example.com/audio/promo-sting.wav",
        "mime_type": "audio/wav"
      }
    ],
    "speech_text": [
      {
        "asset_id": "line_discount",
        "text": "This deal is available for the next ten minutes."
      }
    ],
    "visual_prompts": [
      {
        "asset_id": "gesture_point",
        "text": "point toward the featured product"
      }
    ]
  }
}

{
  "event_id": "evt_asset_add_001",
  "type": "asset.add",
  "assets": {
    "images": [
      {
        "asset_id": "OBJ_0",
        "url": "https://YOUR_CDN.example/speaker.png",
        "mime_type": "image/png",
        "description": "A dark gray cylindrical speaker<OBJ_0> with a perforated grille and a flat base"
      }
    ],
    "audio": [
      {
        "asset_id": "promo_sting",
        "url": "https://cdn.example.com/audio/promo-sting.wav",
        "mime_type": "audio/wav"
      }
    ],
    "speech_text": [
      {
        "asset_id": "line_discount",
        "text": "This deal is available for the next ten minutes."
      }
    ],
    "visual_prompts": [
      {
        "asset_id": "gesture_point",
        "text": "point toward the featured product"
      }
    ]
  }
}

Registers image references and reusable script assets during a session. Assets are additive: existing asset_id values cannot be changed or replaced in v1. If any asset in the event is invalid, none of the assets in that event are registered. Wait for asset.added before referencing the new ids from response.script.

Event fields

string

Client-generated id for this event.

string

required

Event type. Must be asset.add.

object

required

Assets to register for object interaction or later scripted responses. Provide at least one asset across images, audio, speech_text, or visual_prompts.

array

Object reference images for visual interaction.

string

required

Object reference ID, unique across session assets. Use OBJ_0, OBJ_1, and so on.

string

required

HTTPS URL for the image file.

string

Image MIME type, such as image/png or image/jpeg.

string

Optional visual description. If provided, include the matching tag, such as a dark gray cylindrical speaker<OBJ_0> for asset_id: "OBJ_0". Describe the object’s visible shape, color, and distinctive features. See Object interaction.

array

Reusable audio files for response.script.vocal.type: "audio_asset".

string

required

Caller-defined audio asset id, unique within the session.

string

required

HTTPS URL for the audio file. The URL must be directly fetchable by Vivix without custom request headers.

string

Audio MIME type. Supported values are audio/wav and audio/mpeg.

array

Reusable exact speech text for response.script.vocal.type: "speech_asset".

string

required

Caller-defined speech text asset id, unique within the session.

string

required

Exact text to synthesize. When used in response.script, it also streams through output text events.

string

Text format. Use text; SSML is not supported.

array

Reusable visual instructions for response.script.visual.visual_prompt_asset_id.

string

required

Caller-defined visual prompt asset id, unique within the session.

string

required

Reusable visual instruction text describing avatar movement, posture, gaze, gestures, or presentation.

string

Text format, such as text.

{
  "event_id": "evt_asset_add_001",
  "type": "asset.add",
  "assets": {
    "images": [
      {
        "asset_id": "OBJ_0",
        "url": "https://YOUR_CDN.example/speaker.png",
        "mime_type": "image/png",
        "description": "A dark gray cylindrical speaker<OBJ_0> with a perforated grille and a flat base"
      }
    ],
    "audio": [
      {
        "asset_id": "promo_sting",
        "url": "https://cdn.example.com/audio/promo-sting.wav",
        "mime_type": "audio/wav"
      }
    ],
    "speech_text": [
      {
        "asset_id": "line_discount",
        "text": "This deal is available for the next ten minutes."
      }
    ],
    "visual_prompts": [
      {
        "asset_id": "gesture_point",
        "text": "point toward the featured product"
      }
    ]
  }
}

Overview

A1: Streaming Avatar

W1: Streaming World

Blazing Fast Video Generation

Event fields