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

hjunior29 /video-text-generator:940c5d68

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 to add captions to
style_preset
None
tiktok
Caption style preset. Each preset has unique colors, fonts and animations.
font_size
integer
48

Min: 16

Max: 120

Font size for captions (16-120)
highlight_color
string
#39E508
Color for the active word in karaoke mode (hex color)
text_color
string
#FFFFFF
Color for inactive words (hex color)
stroke_color
string
#000000
Color for text outline/stroke (hex color)
stroke_width
integer
5

Max: 15

Width of text outline (0 = no outline)
position
None
bottom
Vertical position of captions
position_y
integer
85

Min: 5

Max: 95

Custom Y position (% from top, only used when position='custom')
animation_style
None
bounce
Animation style for caption entrance
words_per_line
integer
4

Min: 1

Max: 10

Maximum words to show per caption line
background_style
None
none
Background style behind captions
background_color
string
#000000
Background color (for solid/gradient, with opacity)
background_opacity
number
0.6

Max: 1

Background opacity (0-1)
model
None
large-v3
Whisper model size
language
None
auto
Language spoken in the audio
temperature
number
0
Temperature for sampling
condition_on_previous_text
boolean
True
Use previous output as context for next window

Output schema

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

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