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

thomasmol /whisper-diarization:68e6a844

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
file_string
string
Base64 encoded audio file
file_url
string
An audio file URL
file
string
An audio file
offset_seconds
integer
0
Offset in seconds, used for chunked inputs
chunk_index
integer
0
Index of chunk
chunk_count
integer
1

Min: 1

Number of chunks
num_speakers
integer
2

Min: 1

Max: 25

Number of speakers
webhook_id
string
Webhook ID
filename
string
Filename, only needed if file_string is provided
prompt
string
some people speaking
Prompt, to be used as context

Output schema

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

Schema
{'properties': {'chunk_count': {'title': 'Chunk Count', 'type': 'integer'},
                'chunk_index': {'title': 'Chunk Index', 'type': 'integer'},
                'file_url': {'title': 'File Url', 'type': 'string'},
                'offset_seconds': {'title': 'Offset Seconds',
                                   'type': 'integer'},
                'segments': {'title': 'Segments'},
                'webhook_id': {'title': 'Webhook Id', 'type': 'string'}},
 'required': ['webhook_id',
              'file_url',
              'offset_seconds',
              'chunk_index',
              'chunk_count'],
 'title': 'ModelOutput',
 'type': 'object'}