FlowSync
Open App
中文
ProAudio & Video7 nodes
Score 78

AI Video Generation Workflow

Turn text, files, or URLs into finished narrated videos — storyboard, voiceover, subtitles, dual-ratio MP4 output — in one 7-node automated pipeline.

Run this template Fork & customise

What does this workflow do?

Drop your text — the pipeline runs 7 automated steps: LLM Reasoning (text→json) → LLM Reasoning (json→json) → Pillow (image→image) → LLM Reasoning (json→srt) → LLM Reasoning (json→html) → HyperFrames (html→mp4) → MoviePy (mp4→mp4) — and delivers mp4. Every node is visible, auditable, and replaceable.

System flow

1. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 2. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 3. Pillow — Image pre-processing — deskew, denoise, crop and normalise before analysis 4. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 5. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 6. HyperFrames — Frame-accurate HTML animation engine driving the visual timeline 7. MoviePy — Video encode and post — multi-ratio export, audio mix, MP4 output

Pipeline breakdown

LLM Reasoning text LLM Reasoning json Pillow image LLM Reasoning json LLM Reasoning json HyperFrames html MoviePy mp4
  1. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output text → json
  2. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → json
  3. Pillow pillow — Image pre-processing — deskew, denoise, crop and normalise before analysis image → image
  4. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → srt
  5. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → html
  6. HyperFrames hyperframes — Frame-accurate HTML animation engine driving the visual timeline html → mp4
  7. MoviePy moviepy — Video encode and post — multi-ratio export, audio mix, MP4 output mp4 → mp4

Workflow Reputation Score

Based on executions, success rate, update frequency, component quality, and user rating.

78Overall
★★★★★ 4.6
▶Executions
30
✓Success rate
100
↻Update frequency
85
⚙Component quality
96
★User rating
92

Based on executions, success rate, update frequency, component quality, and user rating.

Components used

LLM Reasoningllm

Large-language-model step that extracts, classifies, validates or writes structured output

FlowSync proprietary
Pillowpillow

Image pre-processing — deskew, denoise, crop and normalise before analysis

python-pillow/Pillow ↗
HyperFrameshyperframes

Frame-accurate HTML animation engine driving the visual timeline

flowlab/hyperframes ↗
MoviePymoviepy

Video encode and post — multi-ratio export, audio mix, MP4 output

Zulko/moviepy ↗

How is this different from n8n or Zapier?

Unlike generic workflow builders, FlowSync workflows ship pre-configured with AI skills baked into every node — OCR, LLM reasoning, transcription, super-resolution — not just webhook triggers. Each node is white-box auditable: you see input, output, and config. Deployment is instant — no self-hosting, no API-key per node.

Author & Source

This workflow is maintained by the FlowSync team. All components are open-source or commercially licensed. Source code for each component is linked in the Components section above.

Pricing: Free tier available · 30% commission on forks · PRO tier · Official

FlowSync Workflow Marketplace · 78 reputation score · 30% execution · 100% success · 7-node white-box pipeline · maintained by FlowSync Official

Ready to run?

Turn text, files, or URLs into finished narrated videos — storyboard, voiceover, subtitles, dual-ratio MP4 output — in one 7-node automated pipeline.

Run Text/file/URL → professional video (7-la → Browse all workflows →