synthesys-ai / synthesys-sonic

  • Public
  • 8.5K runs
  • H100
Iterate in playground

Run synthesys-ai/synthesys-sonic 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
image
string
Path to the input image
audio
string
Path to the input audio file
weight_dtype
string (enum)

Options:

fp16, fp32, bf16

An enumeration.
dynamic_scale
number
1
Dynamic scaling factor for processing
audio_guidance_scale
number
7.5
Audio guidance scaling factor for processing
crop
boolean
False
Crop the image around the detected face
seed
integer
Random seed for reproducibility
min_resolution
integer
512
Minimum resolution for output video
inference_steps
integer
25
Number of inference steps to process

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"
}