fictions-ai / autocaption

Automatically add captions to a video

  • Public
  • 35K runs
  • L40S
  • GitHub
  • Paper
  • License

Input

*file
Preview

Video file

file

Transcript file, if provided will use this for words rather than whisper.

boolean

Output video, if true will output the video with subtitles

Default: true

boolean

Output transcript json, if true will output a transcript file that you can edit and use for the next run in transcript_file_input

Default: true

string

Subtitles position

Default: "bottom75"

string
Shift + Return to add a new line

Caption color

Default: "white"

string
Shift + Return to add a new line

Highlight color

Default: "yellow"

number

Font size. 7.0 is good for videos, 4.0 is good for reels

Default: 7

integer

Max characters space for subtitles. 20 is good for videos, 10 is good for reels

Default: 20

number

Opacity for the subtitles background

Default: 0

string

Font

Default: "Poppins/Poppins-ExtraBold.ttf"

string
Shift + Return to add a new line

Stroke color

Default: "black"

number

Stroke width

Default: 2.6

number

Kerning for the subtitles

Default: -5

boolean

Right to left subtitles, for right to left languages. Only Arial fonts are supported.

Default: false

boolean

Translate the subtitles to English

Default: false

Output

Generated in

This example was created by a different version, fictions-ai/autocaption:aa083d4a.

Run time and cost

This model costs approximately $0.10 to run on Replicate, or 10 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 105 seconds. The predict time for this model varies significantly based on the inputs.