Optional videoURL of the video to analyse. Mutually exclusive with videoBuffer.
Optional videoRaw video bytes. Mutually exclusive with videoUrl.
Optional promptText prompt / question to guide the analysis (e.g. "Describe the key actions in this video").
Optional modelModel identifier to use for the vision LLM analysis step.
Optional maxMaximum number of frames to sample for analysis.
Optional sceneThreshold for scene change detection (0-1). Lower values detect more scene boundaries (more sensitive); higher values only detect dramatic cuts.
0.3
Optional transcribeWhether to transcribe the audio track using the configured STT provider.
true
Optional descriptionHow detailed scene descriptions should be.
'detailed'
Optional maxMaximum number of scenes to detect. Prevents runaway analysis on very long videos.
100
Optional indexWhether to index scene descriptions and transcripts into the RAG vector store for later retrieval.
false
Optional onOptional callback invoked as analysis progresses through phases.
Optional providerArbitrary provider-specific options.
Optional usageOptional durable usage ledger configuration for accounting.
Options for a analyzeVideo call.
At minimum, a video source (
videoUrlorvideoBuffer) is required.