SASuraj Kiran Airi
  • About
  • Projects
  • Certificates

© 2026 Suraj Kiran Airi. Built with Next.js and Tailwind.

  • Email
  • Resume
  • LinkedIn
  • GitHub
All projects
AI, Full stackFeb 2026 - PresentWeb app, CLI

Zensho - AI-Powered Desktop Video Editor

Desktop app that transcribes footage, AI-generates rough cuts, and exports editable timelines to DaVinci Resolve.

Live DemoGitHub
MacOS app showing rough-cut paragraph view

MacOS app showing rough-cut paragraph view

The problem

Turning raw screencast or facecam footage into a usable rough cut means manually scrubbing through hours of audio to cut stutters, dead air, and rambling takes — tedious work that delays the creative editing that actually matters, and most AI editing tools lock footage into a cloud pipeline or a proprietary subscription instead of a professional NLE workflow.

The result

Built a full desktop application that transcribes footage, uses an LLM to make AI-driven keep/cut decisions, and exports either directly or as a fully editable OpenTimelineIO timeline for DaVinci Resolve — with a custom LCS-based text-to-timestamp aligner and waveform-aware boundary snapping so cuts land on natural pauses rather than mid-word or mid-syllable.

How it works

Zensho is a hybrid desktop application: an Electron/React/Vite frontend drives a locally-spawned Python FastAPI backend over HTTP (bound to 127.0.0.1 for local-only traffic), chosen specifically so CPU/IO-heavy ffmpeg and transcription work never blocks the UI thread. The processing pipeline runs each video through ffmpeg audio extraction, Deepgram Nova-3 word-level transcription, and an LLM rough-cut pass (via LiteLLM, so any OpenAI-compatible or BYOK provider can be swapped in) that decides what to keep, cut, or treat as silence.

Key technical achievements include:

  • Custom LCS-based transcript aligner: the LLM returns only the words worth keeping, and a hand-written Longest-Common-Subsequence dynamic-programming aligner maps that refined script back onto the original word-level timestamps, with 'last-occurrence-wins' tie-breaking so repeated takes resolve to the correct (latest) occurrence, and a minimum-LCS-ratio fallback that preserves all content rather than silently discarding it if the LLM paraphrases instead of cutting.
  • Waveform-aware boundary snapping: a separate preprocessor snaps every cut point to the nearest word boundary and then refines further by extracting a PCM window via ffmpeg and finding the minimum-RMS-energy point, so cuts fall in natural pauses instead of mid-syllable — with a repair pass that clamps overlaps and removes now-redundant silence segments between adjacent kept clips.
  • Serialized async processing queue: a singleton asyncio.Queue worker processes one video at a time through a QUEUED → PREPROCESSING → TRANSCRIBING → ROUGH_CUTTING → COMPLETED state machine, preventing concurrent ffmpeg instances and LLM rate-limit bans while the UI polls a /status endpoint for live progress.
  • Non-destructive DaVinci Resolve export: an OpenTimelineIO exporter builds a multi-FPS-safe .otio timeline (plus FCP XML) from the same 'resolved timeline' used for the in-app preview player and MP4 export, linking video/audio clips via matching reel metadata so Resolve treats them as synced pairs — letting editors drag the AI's decisions straight into a professional NLE with every cut still editable.
  • Human-in-the-loop editing model: AI-generated cuts (rough_cut_ai) are never overwritten — user edits are stored as a separate rough_cut_human layer, with all exporters resolving rough_cut_human ?? rough_cut_ai per video, so some clips in a project can carry human edits while others still use the raw AI cut.
  • Dual interface: the same backend core is exposed both through the Electron desktop app and a standalone CLI (run, process, export, status, config) for scripted or headless use.

Tech stack

  • TypeScript
  • React
  • Vite
  • Electron
  • Tailwind CSS
  • Python 3.12+
  • FastAPI
  • Uvicorn
  • Pydantic
  • asyncio
  • Deepgram SDK
  • LiteLLM
  • OpenTimelineIO
  • ffmpeg
  • loguru

Tags

  • Electron
  • FastAPI
  • LLM Integration
  • LiteLLM
  • Deepgram
  • OpenTimelineIO
  • LCS Sequence Alignment
  • Waveform Analysis
  • Async Processing Queue
  • IPC Context Bridge
  • BYOK
  • ffmpeg
  • Pydantic
  • State Machine Design