zsxkib/smart-thinksound | API reference

Automatically generates expert ThinkSound prompts by analyzing your video w/ Claude 4 - no more struggling with complex audio descriptions

Public

458 runs

Run with an API

Playground API Examples README

Run zsxkib/smart-thinksound 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
video	string		Silent video to enrich with AI-generated audio
context_hint	string		Optional context hint for ambiguous scenes (e.g., 'fireworks', 'machinery', 'wildlife')
cfg_scale	number	5 Min: 1 Max: 20	Guidance scale for audio generation
num_inference_steps	integer	24 Min: 10 Max: 100	Number of inference steps
seed	integer		Seed for reproducible results

{
  "type": "object",
  "title": "Input",
  "required": [
    "video"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 4,
      "nullable": true,
      "description": "Seed for reproducible results"
    },
    "video": {
      "type": "string",
      "title": "Video",
      "format": "uri",
      "x-order": 0,
      "description": "Silent video to enrich with AI-generated audio"
    },
    "cfg_scale": {
      "type": "number",
      "title": "Cfg Scale",
      "default": 5,
      "maximum": 20,
      "minimum": 1,
      "x-order": 2,
      "description": "Guidance scale for audio generation"
    },
    "context_hint": {
      "type": "string",
      "title": "Context Hint",
      "default": "",
      "x-order": 1,
      "description": "Optional context hint for ambiguous scenes (e.g., 'fireworks', 'machinery', 'wildlife')"
    },
    "num_inference_steps": {
      "type": "integer",
      "title": "Num Inference Steps",
      "default": 24,
      "maximum": 100,
      "minimum": 10,
      "x-order": 3,
      "description": "Number of inference steps"
    }
  }
}

Output schema

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

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}

Example API response

View prediction

'https://replicate.delivery/xezq/fpt97GQvKej4VkadUizz84xsWQmfw6lJoRpflVeOutKXKy9nC/tmpbqcd3hk4.mp4'