You're looking at a specific version of this model. Jump to the model overview.

zsxkib /multitalk:0bd2390c

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
Reference image containing the person(s) for video generation
first_audio
string
First audio file for driving the conversation
prompt
string
A smiling man and woman wearing headphones sit in front of microphones, appearing to host a podcast.
Text prompt describing the desired interaction or conversation scenario
second_audio
string
Second audio file for multi-person conversation (optional)
num_frames
integer
81

Min: 25

Max: 201

Number of frames to generate (automatically adjusted to nearest valid value of form 4n+1, e.g., 81, 181)
sampling_steps
integer
40

Min: 2

Max: 100

Number of sampling steps (higher = better quality, lower = faster)
seed
integer
Random seed for reproducible results
turbo
boolean
True
Enable turbo mode optimizations (adjusts thresholds and guidance scales for speed)

Output schema

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

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}