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

ahmad-tijjani-garba /avdsec:c3e705f0

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
video
string
Video file (MP4, MOV, MKV, WebM, ...). English dialogue.
subtitles
string
Optional English subtitles (.srt or .vtt; if the upload form " "refuses .srt, rename it to .txt): exact dialogue timing and " "names.
subtitles_text
string
Optional: paste the subtitles (SRT or WebVTT text) here instead of " "uploading a file.
cast
string
Optional characters, e.g. 'Lisbeth (young woman, black hair); " "Mikael (man in his 40s, glasses)'.
video_context
string
Optional type of video, e.g. 'crime drama film'.
density
None
standard
How many descriptions: standard is what the pipeline was evaluated with.
voice
None
af_heart
Narration voice (Kokoro): a = American, b = British; f = female, m = male.
speed
number
1

Min: 0.7

Max: 1.4

Narration speed (1.0 = normal).
show_descriptions
boolean
True
Draw the description text into the picture (top).
show_captions
boolean
True
Draw the dialogue captions into the picture (bottom).

Output schema

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

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