← All projects
Content

OpenCut v3

Multi-domain short-video platform

Overview

OpenCut v3 turns still images into 1080×1920 vertical short videos through a 20-stage AI-assisted pipeline. Domain configuration (education, travel, knowledge_paid, custom) drives prompt packs and storyboards so each output feels native to its niche.

TTS + BGM matching + auto-captions + Remotion rendering, with CLI and SaaS dual-track distribution.

Product impact

Pain → Solution → Value

Short-form video production is stitched together from five different tools — script, voice, audio–visual alignment, face-aware cuts, BGM. OpenCut v3 collapses that pipeline into a single pass: image assets in, finished 1080×1920 vertical video out, with the right domain config to keep quality consistent across niches.

Pain
5 tools, 1 video
Script, voice, align, face, BGM.
Solution
Single pipeline
One pass, one output.
5 → 1
Tools → 1 pipeline
Pain
Manual stitching slow
Round-trip across 5 apps.
Solution
End-to-end automation
Image folder in, video out.
1
Pipeline, 1080×1920 output
Pain
Domain-specific quality varies
Education ≠ travel ≠ knowledge_paid.
Solution
Domain-config-driven
Tone, pacing, visual style locked.
1
Config per vertical
Pain
Subtitle + voice + BGM separate
Dropped frames, audio drift.
Solution
Integrated compose step
Subtitle, voice, BGM aligned in one pass.
0
Manual steps

What changes for the team

A wider view of the same loop. Each card zooms into the corresponding column above.

Pain

Short-form production is stitched, not made

  • Script writing, voice synthesis, audio–visual alignment, face-aware cuts, BGM — five separate tools.
  • Operators stitch outputs manually; the round-trip is slow and error-prone.
  • Quality drifts every time the domain changes — education vs. travel vs. knowledge_paid.
5
Separate tools per output
Solution

Drop images in, ship 1080×1920 out

  • Drop in a folder of still images + a domain config — OpenCut v3 produces a finished vertical video in one pass.
  • Voiceover, subtitles, BGM already composed — no manual stitching, no per-tool context switching.
  • Domain presets lock tone, pacing, and visual style for every niche.
1080×1920
Vertical output, one pass
Value

Ship in hours, quality stays native per niche

  • Content teams ship short-form videos in hours instead of days.
  • Domain presets lock tone, pacing, and visual style so every output feels native.
  • Zero manual stitching means zero dropped frames between cuts.
0
Manual stitching steps

Product architecture

A five-stage pipeline turns image assets and a domain config into a finished 1080×1920 short video. Each stage has a single, well-defined responsibility; arrows mark data flow from raw assets to final render.

1

Script

An LLM ingests the domain config (education / travel / knowledge_paid / custom) plus the image set, then writes a narration script and a shot-by-shot storyboard tuned to that niche.

LLM · domain config
2

Voice

edge-tts synthesizes the narration into a clean voiceover track with the chosen language and voice profile, ready for downstream alignment.

edge-tts
3

Align

PyTorch + Transformers score each still image against the audio track and pick the shot that best matches the current beat, producing a tightly cut visual timeline.

PyTorch · Transformers
4

Detect

OpenCV runs face detection on each frame to find faces, then places camera cuts and framing so the subject stays centered and well-composed.

OpenCV
5

Compose

The final renderer lays BGM underneath, burns auto-generated subtitles over the voiceover, and writes the finished 1080×1920 vertical video to disk — ready to publish.

BGM + subtitles

Technical architecture

AI video production pipeline. Click any node or relationship for details.

Capabilities

Domain presets
education / travel / knowledge_paid / custom.
TTS + Remotion
Speech, auto-subtitles, BGM matching.
Dual distribution
CLI for batch; SaaS for one-off.
Pipeline observability
20 stages with progress events.

By the numbers

  • 20-stage pipeline
  • 4 domains
  • 1080×1920 vertical
  • TTS + auto-captions
  • BGM matching
  • CLI + SaaS

Try it, fork it, or hire me to extend it.

Source on GitHub · {p['license']} · questions to 286043314+echocc00@users.noreply.github.com