You're looking at a specific version of this model. Jump to the model overview.
hjunior29 /video-text-generator:6a5d0f09
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 process
|
|
| layers_json |
string
|
|
JSON configuration for text layers. Example:
{
"layers": [
{
"type": "text",
"content": "MY TITLE",
"startMs": 0,
"endMs": 3000,
"position": {"x": 50, "y": 20},
"style": {"fontSize": 64, "color": "#FFFFFF"},
"animation": {"enter": {"type": "bounceIn", "duration": 500}}
},
{
"type": "caption",
"source": "whisper",
"position": {"x": 50, "y": 85},
"karaoke": true
}
]
}
Leave empty to use simple mode with parameters below.
|
| generate_captions |
boolean
|
True
|
Generate captions from audio using Whisper AI
|
| caption_preset |
None
|
tiktok
|
[Simple Mode] Caption style preset
|
| caption_position |
None
|
bottom
|
[Simple Mode] Caption vertical position
|
| font_size |
integer
|
48
Min: 16 Max: 120 |
[Simple Mode] Font size for captions
|
| highlight_color |
string
|
#39E508
|
[Simple Mode] Karaoke highlight color (hex)
|
| text_color |
string
|
#FFFFFF
|
[Simple Mode] Base text color (hex)
|
| animation_style |
None
|
bounce
|
[Simple Mode] Caption entrance animation
|
| language |
None
|
auto
|
Language spoken in the audio (for captions)
|
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'}