🔄 YouTube Caption
Unified YouTube caption extraction and processing workflow. Consolidates youtube_caption_extraction_v1 and youtube_caption_processing_v1 into a single template using the youtube_pipeline processor's built-in modes. Modes (controlled by processor_config.mode): - caption_only: Extract captions (replaces youtube_caption_extraction_v1) - caption_with_text_processing: Extract + text normalization - caption_with_structure: Extract + processing + LLM structure extraction - full_pipeline: Complete processing (replaces youtube_caption_processing_v1) v2 improvements: - Integrated paragraphize support (previously CLI-only) - Single-step architecture aligned with engine capabilities - Timestamp-aware paragraph breaking - All processing modes in one template
Template Information
- Workflow ID
youtube_caption_v2- Version
- 2.0.0
- Status
- Active
- Author
- AECS4U Ocular Team
- Created
- 2026-02-26T00:00:00Z
- Steps
- 1
- Tags
- youtube captions transcription video text-processing paragraphize unified v2 production
Input Schema
video_url- str
language- str
Instance Presets
0No instances defined for this template
Workflow Flowchart
Workflow Steps
- Step ID
youtube_pipeline- Processor Type
- python
- Timeout
- 120s
- Max Retries
- 3
- Retry on Failure
- Yes
- Cache Results
- Yes
Input Mapping
| Target Parameter | Source Value |
|---|---|
video_url |
video_url |
language |
language |