shridharathi/ugc-avatar | API reference

Public

2 runs

Run shridharathi/ugc-avatar with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
prompt	string		Name of the product to promote
avatar_image	string		Portrait image of the person who will be the talking avatar
product_name	string		Name of the product to promote
product_description	string		Description of the product and its benefits
brand_name	string		Name of the brand
target_audience	string	general consumers	Target audience for the product (e.g., 'fitness enthusiasts', 'busy professionals', 'students')
video_length	None	30 seconds	Desired length of the promotional video
tone	None	enthusiastic	Tone of voice for the script
voice_id	None	Friendly_Person	Voice to use for speech synthesis
emotion	None	happy	Emotion for the speech
voice_speed	number	1 Min: 0.8 Max: 2	Speech rate for lip sync
sound_effects_intensity	None	medium	Intensity of background sound effects
seed	integer		Random seed for reproducible results

{
  "type": "object",
  "title": "Input",
  "required": [
    "prompt",
    "avatar_image",
    "product_name",
    "product_description",
    "brand_name"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 12,
      "nullable": true,
      "description": "Random seed for reproducible results"
    },
    "tone": {
      "enum": [
        "enthusiastic",
        "professional",
        "casual",
        "friendly",
        "authoritative"
      ],
      "type": "string",
      "title": "tone",
      "description": "Tone of voice for the script",
      "default": "enthusiastic",
      "x-order": 7
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 0,
      "description": "Name of the product to promote"
    },
    "emotion": {
      "enum": [
        "auto",
        "neutral",
        "happy",
        "sad",
        "angry",
        "fearful",
        "disgusted",
        "surprised"
      ],
      "type": "string",
      "title": "emotion",
      "description": "Emotion for the speech",
      "default": "happy",
      "x-order": 9
    },
    "voice_id": {
      "enum": [
        "Wise_Woman",
        "Friendly_Person",
        "Inspirational_girl",
        "Deep_Voice_Man",
        "Calm_Woman",
        "Casual_Guy",
        "Lively_Girl",
        "Patient_Man",
        "Young_Knight",
        "Determined_Man",
        "Lovely_Girl",
        "Decent_Boy",
        "Imposing_Manner",
        "Elegant_Man",
        "Abbess",
        "Sweet_Girl_2",
        "Exuberant_Girl"
      ],
      "type": "string",
      "title": "voice_id",
      "description": "Voice to use for speech synthesis",
      "default": "Friendly_Person",
      "x-order": 8
    },
    "brand_name": {
      "type": "string",
      "title": "Brand Name",
      "x-order": 4,
      "description": "Name of the brand"
    },
    "voice_speed": {
      "type": "number",
      "title": "Voice Speed",
      "default": 1,
      "maximum": 2,
      "minimum": 0.8,
      "x-order": 10,
      "description": "Speech rate for lip sync"
    },
    "avatar_image": {
      "type": "string",
      "title": "Avatar Image",
      "format": "uri",
      "x-order": 1,
      "description": "Portrait image of the person who will be the talking avatar"
    },
    "product_name": {
      "type": "string",
      "title": "Product Name",
      "x-order": 2,
      "description": "Name of the product to promote"
    },
    "video_length": {
      "enum": [
        "15 seconds",
        "30 seconds",
        "60 seconds"
      ],
      "type": "string",
      "title": "video_length",
      "description": "Desired length of the promotional video",
      "default": "30 seconds",
      "x-order": 6
    },
    "target_audience": {
      "type": "string",
      "title": "Target Audience",
      "default": "general consumers",
      "x-order": 5,
      "description": "Target audience for the product (e.g., 'fitness enthusiasts', 'busy professionals', 'students')"
    },
    "product_description": {
      "type": "string",
      "title": "Product Description",
      "x-order": 3,
      "description": "Description of the product and its benefits"
    },
    "sound_effects_intensity": {
      "enum": [
        "subtle",
        "medium",
        "dynamic"
      ],
      "type": "string",
      "title": "sound_effects_intensity",
      "description": "Intensity of background sound effects",
      "default": "medium",
      "x-order": 11
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "final_video",
    "script",
    "audio",
    "sound_effects_audio"
  ],
  "properties": {
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri"
    },
    "script": {
      "type": "string",
      "title": "Script"
    },
    "final_video": {
      "type": "string",
      "title": "Final Video",
      "format": "uri"
    },
    "sound_effects_audio": {
      "type": "string",
      "title": "Sound Effects Audio",
      "format": "uri"
    }
  }
}