# anpramila95/whiteboard-video architecture

> Architecture diagram of the GitHub repository anpramila95/whiteboard-video, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/anpramila95/whiteboard-video
- Repository: https://github.com/anpramila95/whiteboard-video

## Overview

This repository turns a topic, narration script, or existing SRT into a narrated whiteboard-animation video. The principal workflow is agent-guided script and narration preparation, timed subtitle/scene planning, scene illustration and region annotation, per-scene rendering, then video assembly and audio/subtitle finishing. The README documents several human/agent steps whose implementation is not present in the sampled source, so those links are documented workflow relationships rather than claims about inspected code.

Main entry points: [`run_video.py`](https://github.com/anpramila95/whiteboard-video/blob/main/run_video.py) (Video workflow), [`scripts/tts_narration.py`](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/tts_narration.py) (Narration synthesis), [`scripts/parse_srt.py`](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/parse_srt.py) (SRT scene planning), [`scripts/render_stream_whiteboard.py`](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/render_stream_whiteboard.py) (Scene renderer)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_planning["Script and timing"]
  node_skill["Workflow skill<br/>[SKILL.md]"]
  node_script["Script to subtitles<br/>[script_to_srt.py]"]
  node_srt_plan["SRT scene planning<br/>[parse_srt.py]"]
  node_dg_plan["Deepgram segmentation"]
  node_retime["Annotation retiming"]
end

subgraph group_media["Scene assets"]
  node_image_gen["Scene image generation"]
  node_annotations["Region annotations"]
  node_preview["Annotation preview"]
end

subgraph group_render["Whiteboard rendering"]
  node_scene_render["Scene renderer"]
  node_stroke_engine["Stroke renderer<br/>[stream_render.py]"]
end

subgraph group_finish["Video finishing"]
  node_orchestrator["Video workflow<br/>[run_video.py]"]
  node_merge["Scene assembly<br/>[merge_scenes.py]"]
  node_final["Narrated video"]
end

subgraph group_voice["Speech services"]
  node_speech["Narration synthesis<br/>[tts_narration.py]"]
end

node_creator(("Creator / agent"))
node_edge_tts{{"Edge TTS"}}
node_vbee{{"Vbee TTS"}}
node_image_api{{"Image generation API"}}

node_creator -->|"starts workflow"| node_skill
node_skill -->|"creates draft"| node_script
node_script -->|"draft subtitles"| node_speech
node_speech -.->|"synthesizes with"| node_edge_tts
node_speech -->|"synthesizes with"| node_vbee
node_speech -->|"retimes subtitles"| node_srt_plan
node_creator -->|"provides SRT"| node_srt_plan
node_srt_plan -->|"suggests scenes"| node_creator
node_dg_plan -->|"plans scenes"| node_creator
node_creator -->|"requests images"| node_image_gen
node_image_gen -->|"requests images"| node_image_api
node_creator -->|"defines regions"| node_annotations
node_annotations -->|"previews regions"| node_preview
node_creator -->|"renders scene"| node_scene_render
node_scene_render -->|"uses stroke engine"| node_stroke_engine
node_srt_plan -->|"provides timing"| node_retime
node_creator -->|"runs workflow"| node_orchestrator
node_orchestrator -->|"calls synthesis"| node_speech
node_orchestrator -->|"calls renderer"| node_scene_render
node_orchestrator -->|"calls assembly"| node_merge
node_merge -->|"joins scenes"| node_final
node_orchestrator -->|"adds narration"| node_final

click node_skill "https://github.com/anpramila95/whiteboard-video/blob/main/SKILL.md"
click node_script "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/script_to_srt.py"
click node_speech "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/tts_narration.py"
click node_srt_plan "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/parse_srt.py"
click node_dg_plan "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/segment_deepgram.py"
click node_image_gen "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/batch_generate_images.py"
click node_preview "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/render_annotation_preview.py"
click node_scene_render "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/render_stream_whiteboard.py"
click node_stroke_engine "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/stream_render.py"
click node_retime "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/retime_annotations.py"
click node_orchestrator "https://github.com/anpramila95/whiteboard-video/blob/main/run_video.py"
click node_merge "https://github.com/anpramila95/whiteboard-video/blob/main/scripts/merge_scenes.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_skill,node_script,node_srt_plan,node_dg_plan,node_retime toneBlue
class node_image_gen,node_annotations,node_preview toneAmber
class node_scene_render,node_stroke_engine,node_image_api toneMint
class node_orchestrator,node_merge,node_final toneRose
class node_speech,node_creator,node_edge_tts,node_vbee toneIndigo
```

## Components

### Script and timing

- [Workflow skill](https://github.com/anpramila95/whiteboard-video/blob/main/SKILL.md): `SKILL.md`
- [Script to subtitles](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/script_to_srt.py): `scripts/script_to_srt.py`
- [SRT scene planning](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/parse_srt.py): `scripts/parse_srt.py`
- [Deepgram segmentation](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/segment_deepgram.py): `scripts/segment_deepgram.py`
- [Annotation retiming](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/retime_annotations.py): `scripts/retime_annotations.py`

### Scene assets

- [Scene image generation](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/batch_generate_images.py): `scripts/batch_generate_images.py`
- **Region annotations**
- [Annotation preview](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/render_annotation_preview.py): `scripts/render_annotation_preview.py`

### Whiteboard rendering

- [Scene renderer](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/render_stream_whiteboard.py): `scripts/render_stream_whiteboard.py`
- [Stroke renderer](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/stream_render.py): `scripts/stream_render.py`

### Video finishing

- [Video workflow](https://github.com/anpramila95/whiteboard-video/blob/main/run_video.py): `run_video.py`
- [Scene assembly](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/merge_scenes.py): `scripts/merge_scenes.py`
- **Narrated video**

### Speech services

- [Narration synthesis](https://github.com/anpramila95/whiteboard-video/blob/main/scripts/tts_narration.py): `scripts/tts_narration.py`

### Other components

- **Creator / agent**
- **Edge TTS**
- **Vbee TTS**
- **Image generation API**

## Connections

- Creator / agent → Workflow skill: starts workflow (evidence: `README.md`)
- Workflow skill → Script to subtitles: creates draft (evidence: `README.md`)
- Script to subtitles → Narration synthesis: draft subtitles (evidence: `README.md`)
- Narration synthesis → Edge TTS: synthesizes with (evidence: `README.md`)
- Narration synthesis → Vbee TTS: synthesizes with (evidence: `scripts/tts_narration.py`)
- Narration synthesis → SRT scene planning: retimes subtitles (evidence: `scripts/tts_narration.py`)
- Creator / agent → SRT scene planning: provides SRT (evidence: `README.md`)
- SRT scene planning → Creator / agent: suggests scenes (evidence: `README.md`)
- Deepgram segmentation → Creator / agent: plans scenes (evidence: `scripts/segment_deepgram.py`)
- Creator / agent → Scene image generation: requests images (evidence: `README.md`)
- Scene image generation → Image generation API: requests images (evidence: `scripts/batch_generate_images.py`)
- Creator / agent → Region annotations: defines regions (evidence: `README.md`)
- Region annotations → Annotation preview: previews regions (evidence: `README.md`)
- Creator / agent → Scene renderer: renders scene (evidence: `README.md`)
- Scene renderer → Stroke renderer: uses stroke engine (evidence: `scripts/render_stream_whiteboard.py`)
- SRT scene planning → Annotation retiming: provides timing (evidence: `scripts/retime_annotations.py`)
- Creator / agent → Video workflow: runs workflow (evidence: `README.md`)
- Video workflow → Narration synthesis: calls synthesis (evidence: `run_video.py`)
- Video workflow → Scene renderer: calls renderer (evidence: `run_video.py`)
- Video workflow → Scene assembly: calls assembly (evidence: `run_video.py`)
- Scene assembly → Narrated video: joins scenes (evidence: `scripts/merge_scenes.py`)
- Video workflow → Narrated video: adds narration (evidence: `README.md`)
