lucataco/qwen2.5-omni-7b:0ca8160f – Run with an API on Replicate

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

lucataco /qwen2.5-omni-7b:0ca8160f

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		Text prompt for the model
image	string		Optional image input
audio	string		Optional audio input
video	string		Optional video input
system_prompt	string	You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech.	System prompt for the model
use_audio_in_video	boolean	True	Whether to use audio in video
voice_type	string (enum)	Chelsie Options: Chelsie, Ethan	Voice type for audio output
generate_audio	boolean	True	Whether to generate audio output

Output schema

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

Schema

{'properties': {'text': {'title': 'Text', 'type': 'string'},
                'voice': {'format': 'uri', 'title': 'Voice', 'type': 'string'}},
 'required': ['text'],
 'title': 'Output',
 'type': 'object'}