You're looking at a specific version of this model. Jump to the model overview.
sian-agency /whisper-advanced-plus:31678bca
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 |
|---|---|---|---|
| language |
None
|
Auto-detect
|
Select language for transcription. If not specified, language will be auto-detected. Specifying the language can sometimes improve transcription accuracy.
|
| translate_to |
None
|
None
|
Translate transcript text to target language using DeepL API. Only the plain text transcript will be translated (not timestamps or speaker labels). Select 'None' to disable translation.
|
| audio_url |
string
|
URL of the audio or video file to transcribe (supports mp3, wav, m4a, flac, mp4, mov, etc.)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'description': 'Complete transcription output with all fields.',
'properties': {'detected_language': {'title': 'Detected Language',
'type': 'string'},
'duration': {'nullable': True,
'title': 'Duration',
'type': 'number'},
'segments': {'items': {'additionalProperties': True,
'type': 'object'},
'title': 'Segments',
'type': 'array'},
'segments_speakers': {'items': {'additionalProperties': True,
'type': 'object'},
'nullable': True,
'title': 'Segments Speakers',
'type': 'array'},
'srt': {'title': 'Srt', 'type': 'string'},
'transcript': {'title': 'Transcript', 'type': 'string'},
'translation': {'nullable': True,
'title': 'Translation',
'type': 'string'},
'vtt': {'title': 'Vtt', 'type': 'string'},
'words': {'items': {'additionalProperties': True,
'type': 'object'},
'title': 'Words',
'type': 'array'},
'words_speakers': {'items': {'additionalProperties': True,
'type': 'object'},
'nullable': True,
'title': 'Words Speakers',
'type': 'array'}},
'required': ['transcript',
'detected_language',
'segments',
'words',
'srt',
'vtt'],
'title': 'Output',
'type': 'object'}