lucataco/seamless_communication:b61de43a | Run with an API on Replicate

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

lucataco /seamless_communication:b61de43a

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
task_name	None	S2ST (Speech to Speech translation)	Choose a task
input_audio	string		Provide input file for tasks with speech input: S2ST, S2TT and ASR
input_text	string		Provide input for tasks with text: T2ST and T2TT
input_text_language	None	English	Specify language of the input_text for T2ST and T2TT
target_language_with_speech	None	French	Set target language for tasks with speech output: S2ST or T2ST. Less languages are available for speech compared to text output.
target_language_text_only	None	French	Set target language for tasks with text output only: S2TT, T2TT and ASR.
max_input_audio_length	number	60	Set maximum input audio length.

Output schema

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

Schema

{'properties': {'audio_output': {'format': 'uri',
                                 'title': 'Audio Output',
                                 'type': 'string'},
                'text_output': {'title': 'Text Output', 'type': 'string'}},
 'required': ['text_output'],
 'title': 'Output',
 'type': 'object'}