Video RAG Ingestion - Scenes, Keyframes and Transcript Chunks

Created by

Kanto Labs

Actor

Video to LLM Context - Keyframes, Transcript & Scenes for AI

Prepare videos for a RAG pipeline or vector database: one chunk per scene with its time range, transcript text and a keyframe image link, plus a ready-to-embed llmContext block. Works from n8n, Make or the API. Example: a 21-second public-domain NASA talk.

Try for free

Video to LLM Context - Keyframes, Transcript & Scenes for AIkantolabs/video-to-llm-context

Keyframe grid

File

Status

Duration (s)

+10 fields

Input

Video file URLs(required):https://api.apify.com/v2/key-value-stores/aXcXwfChlioPWAUJv/records/sample-vertical-talk.mp4?signature=105QVevs72w3z5gMQzgIJ

Max scenes / keyframes per video:12

Transcribe speech:true

Max scene length (seconds):30

Output fields

Keyframe grid

File

Status

Duration (s)

Width

Height

FPS

Audio

Scenes

Keyframes

Language

Billed keyframes

Billed audio min

Error

How it works

Sign up on Apify or log in

The Video to LLM Context - Keyframes, Transcript & Scenes for AI Actor is ready to run with the inputs already set for "Video RAG Ingestion - Scenes, Keyframes and Transcript Chunks". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Video RAG Ingestion - Scenes, Keyframes and Transcript Chunks" task

The Video to LLM Context - Keyframes, Transcript & Scenes for AI Actor will start running based on the input automatically. You can also change all the input fields, like video file urls, max scenes / keyframes per video, and more, to match your specific use case.

Receive the "Video RAG Ingestion - Scenes, Keyframes and Transcript Chunks" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as keyframe grid, file, status, and more.