Skip to main content

Documentation Index

Fetch the complete documentation index at: https://na-36-handover-docs-v2-into-docs-v2-dev-20260518.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Prerequisites:
  • Python 3.8+ with pip
  • PyTorch installed (CPU build works for this tutorial)
  • FFmpeg on PATH
  • Go installed (for the http-trickle test tool)
Replace the green tint logic in process_video_async with your own processing: load a PyTorch model in initialize, run inference in process_video_async, and return the output tensor. See for the full API. To connect this service to the Livepeer network, register it as a BYOC container following the same pattern as . You have a working PyTrickle service processing live frames. The FrameProcessor reference covers the full API for VideoFrame, AudioFrame, and session management.

Frame Processor Reference

Full FrameProcessor API: VideoFrame, AudioFrame, update_params, and StreamServer options.

PyTrickle Overview

Architecture, capabilities table, and prerequisites.

ComfyStream as BYOC

How to register a real-time processing service with a Livepeer orchestrator.

Real-Time AI Overview

Cascade architecture and the full request flow.
Last modified on May 19, 2026