Skip to main content
config.video controls how the pipeline samples frames, and detects meaningful changes. Increased sensitivity will capture more images, and a lower sensitivity will capture less images.
Default fields are: screenshot_interval_seconds is 1, sensitivity is 0.1, openai_model is gpt-4.1, whisper_model is whisper-1. You only need to send fields you want to override.
import type { JobInput } from "@trelent/data-ingestion";

const job: JobInput = {
  connector: { type: "url", urls: ["https://signed.example.com/webinar.mp4"] },
  output: { type: "s3-signed-url" },
  config: {
    video: {
      screenshot_interval_seconds: 0.5,
      sensitivity: 0.15,
      openai_model: "gpt-4o-mini",
    },
  },
};

​
Field reference

​
config.video.screenshot_interval_seconds
number
default:"1"
Number of seconds between sampled frames. Lower values capture more context for fast-moving scenes; higher values save cost for static footage.
​
config.video.sensitivity
number
default:"0.1"
Normalized threshold for detecting visual changes. Raise it capture subtle transitions; lower it to ignore small changes.
​
config.video.openai_model
string
default:"gpt-4.1"
LLM used for visual reasoning and summarization. Pick a lighter model (for example, gpt-4o-mini) when you need lower latency.
​
config.video.whisper_model
string
default:"whisper-1"
Model used for audio transcription. Swap this if you require multilingual or domain-specific tuning. Model must support verbose_json output format.
Fine-tune how the system judges frame similarity. The sensitivity field will generate default values for these fields, however if you want more granular control you can override them manually.
​
config.video.tile
integer | null
default:"null"
Tile size for block-based comparisons. Leave null to use the default value tuned for general content.
​
config.video.mad_thresh
number | null
default:"null"
Mean absolute deviation threshold. Lower numbers capture subtle noise at the expense of more detections.
​
config.video.local_ssim_drop
number | null
default:"null"
Triggers when the local SSIM (structural similarity index) drops below the specified value. Helpful for scene-change detection.
​
config.video.max_bad_frac
number | null
default:"null"
Fraction of tiles that can cross the SSIM threshold before the frame counts as “changed.” Lower fractions make detection stricter.