Hey everyone!
We just shipped the biggest update to OpenCut AI since launch, turning it from an AI-powered text editor into a full professional video editor. All open source, all self-hosted.
Here's what's new:
AI Features
- AI Music Generation Pick a genre (15 options), mood (12 options), and tempo. Generate royalty-free background music and drop it on the timeline.
- AI Thumbnail Generator Describe what you want or let AI generate from your transcript. 5 styles, 4 platform sizes, up to 4 variations at once.
- AI Script-to-Video Write a script, AI generates voiceover, creates visuals, and builds the timeline automatically.
- AI Auto-Duck Automatically lowers background music when speech is detected. Configurable duck amount and fade curves.
- AI Auto-Color Correction 8 one-click profiles: Vibrant Pop, Film Look, Warm Sunset, Cool Blue, and more. Batch apply to all clips.
- AI Video-to-Shorts One click to auto-select the best clip, trim to target duration, set 9:16/1:1/4:5 canvas, add subtitles.
-Speaker-Labeled Captions Color-coded speaker labels, rename speakers, apply captions with speaker awareness.
Professional Editor
- 20 transitions Iris Wipe, Clock Wipe, Morph, Glitch, Film Burn, Page Peel, Cube Spin, and more. All WebGL shaders.
- 12 effects + 22 filter presets Sharpen, Chromatic Aberration, Film Grain, Motion Blur, Duotone. Presets: Sunset Glow, Cyberpunk, Film Noir, Retro VHS.
- Crop & Mask Rectangle, ellipse, polygon masks with feather and inversion.
- Multicam Editing Sync angles, switch views with one click.
- Marker System Colored markers with notes, jump between markers.
- J/K/L Shuttle Playback Variable speed reverse and forward (1x-8x).
- Ripple Trim Delete clips and close gaps automatically.
- Compound Clips Nest multiple clips into one, un-nest anytime.
Audio
- Audio Effects Chain Per-track EQ, Compressor, Noise Gate, Reverb, De-esser, Limiter with Web Audio API processing.
- Direct Recording Record audio from your mic directly to the timeline with live level metering.
- LUFS Normalization Measure loudness and normalize to platform targets (YouTube, Spotify, Apple Podcasts, broadcast standards).
- Beat Detection Detect BPM, visualize beats, snap edits to the beat grid.
Workflow
- Batch Export Queue up to 8 platform presets (YouTube 1080p/4K, TikTok 9:16, Instagram, Twitter, Podcast Audio).
- Keyboard Shortcut Editor Full management UI with search, rebind, conflict detection.
- Undo History Panel Visual command history, click to jump to any point.
- Color-Coded Tracks 8 track colors + track locking.
- Filmstrip Thumbnails Cached frame thumbnails on timeline clips.
- Template Gallery 8 project templates (YouTube Intro, TikTok Vlog, Podcast Highlight, etc.).
- Share via Link Generate share links with expiration and password protection.
Why this matters
Every other AI video editor (Descript, CapCut, Runway) sends your footage to the cloud. OpenCut AI runs entirely on your machine. No subscriptions, no data leaving your server, no per-seat pricing.
Self-host on a $20/mo server or run it locally on your laptop or desktop. MIT licensed.
What feature would you want us to build next?

OpenCut AI is the only self-hosted video editor with AI built in. We just added first-class support for MoonshotAI's Kimi K2 a 1T/32B active MoE model that runs entirely locally on TurboQuant.

What makes this different:

• Kimi K2 handles natural language editing commands, script generation, and long-context video analysis all on your hardware

• Three quantization tiers (Q3/Q4/Q5), so it runs on anything from a laptop to a GPU server

• Kimi VL A3B adds vision-language understanding for scene analysis and multimodal commands

• TurboQuant KV cache compression means you can run frontier-class models on 8 GB RAM

Your footage. Your models. Your rules. No cloud.

Hey everyone! Excited to share what we've been working on.
We just added Virality Score to OpenCut AI, a neuroscience-backed engagement analyzer that grades your video A-F across 7 signals before you hit publish.
How it works
Drop a video into the editor, click "Check Virality Score," and get:
- Hook Strength does your first 1.5s grab attention? (33% of TikTok viewers scroll past in 3 seconds)
- Curiosity Gap is there unresolved tension keeping viewers watching?
- Audio Energy are your levels and pacing right for the platform?
- Beat Sync do visual cuts land on audio beats?
- Face Presence the #1 short-form retention driver
- Emotional Arc does your clip build to a payoff or flatline?
- Viral Potential LLM-powered composite prediction
Each signal scores 0-100, rolls into a letter grade, and comes with actionable suggestions ranked by expected impact.
Why we built this
Most creators publish and pray. The difference between 10 views and 100K views is rarely the content it's the presentation. We used neuroscience research (dopamine prediction loops, orienting response, information-as-reward) to identify what actually holds attention, then built scoring algorithms around real platform data:
- 65% of 3-second viewers watch 10+ seconds
- Text overlays increase view time by 28%
- Videos with 65%+ 3-second retention get 4-7x more impressions

Also in this update: YouTube to Reels
Paste a YouTube URL and OpenCutAI will auto-detect the best 15-90s clips, score each one, reframe to 9:16 with face tracking, add captions, and export ready-to-upload reels. The full pipeline runs locally.
Would love to hear from creators, what signals would you add to the scoring? What's the first thing you'd test this on?

Hey ProductHunt!

We just shipped a big batch of features to OpenCut AI, our open-source self-hosted video editor. Here's what's new:

WebGL Transitions

OpenCut-AI just shipped real GPU support for TurboQuant KV cache compression.
OpenCut-AI is an open-source, local-first AI video editor. Everything runs on your machine transcription, voice cloning, image generation, LLM commands. No cloud, no API keys.
The catch was always memory. Running a 7B LLM + Whisper + TTS + Stable Diffusion locally means fighting for every gigabyte of RAM. TurboQuant solves this by compressing the KV cache (the biggest memory hog during inference) by up to 7.3 .
What's new in this release:
User-selectable Compute Mode in Settings AI Optimization. Pick Auto, CPU, or GPU (CUDA).
Real integration with the turboquant-gpu library. The GPU backend runs cuTile fused kernels for the full 2-bit / 3-bit KV compression path. The CPU backend uses a PyTorch fallback with physical-core thread pinning and MKLDNN acceleration.
Live-measured compression ratios in the UI. No more static lookup tables you see the actual compression your backend produced on the last request.
Graceful fallback everywhere. Missing CUDA? Falls back to CPU. Missing cuTile kernels? Falls back to PyTorch. The service always comes up.
Huge thanks to Anirudh Bharadwaj Vangara for the turboquant-gpu library that made the real GPU path possible.
OpenCut-AI: https://github.com/Ekaanth/OpenC...
turboquant-gpu: https://github.com/DevTechJr/tur...

Hey Hunters
We just shipped Google Gemma 4 support, paired with our TurboQuant KV-cache compression engine. That means you can now run Google's any-to-any multimodal models directly inside your editor no API keys, no cloud, no data leaving your machine.
What's new in this drop:
Full Gemma 4 family wired into the hardware-aware model registry:
- Gemma 4 E2B (5B) fits in ~3.5 GB, runs on 8 GB laptops
- Gemma 4 E4B (8B) ~5.5 GB, the new sweet-spot for Pro tier
- Gemma 4 26B MoE (4B active) big-model quality, efficient inference
- Gemma 4 31B Dense top-tier quality for 24 GB+ GPUs
TurboQuant KV-cache compression on every model:
- 3.8 compression at 4-bit (cosine similarity 0.9986 effectively lossless)
- 5.0 compression at 3-bit
- 7.3 compression at 2-bit for extreme memory savings
- Unlocks long-context editing sessions (32K 131K tokens) on consumer hardware
Hardware-aware auto-selection OpenCutAI detects your RAM/VRAM and picks the largest Gemma model that'll actually run smoothly. No guesswork.
Served through both Ollama (for simple local use) and our TurboQuant service
Why this matters:
Local video AI has always been a RAM problem. An 8B multimodal model + a long edit timeline + Whisper + TTS used to blow past 16 GB easily. With TurboQuant compressing the KV cache, you can now run Gemma 4 E4B end-to-end on a MacBook with room to spare.
Try it, tear it apart, tell us what breaks

Hey everyone!
We just shipped TurboQuant into OpenCut AI, and this one changes what hardware you need to run the full AI stack.
The problem we had
OpenCut AI runs everything locally -- LLM, transcription, voice cloning, image generation. That's great for privacy, but brutal on memory. Running the full stack needed 35+ GB RAM. Most of our users have 8-16 GB laptops, so they were stuck with tiny 1B models that gave mediocre scripts, slow commands, and limited context.
What TurboQuant does
TurboQuant implements two algorithms from Google Research paper PolarQuant and QJL. That compress the KV cache (the biggest memory bottleneck during AI inference) by up to 6x with mathematically proven quality preservation.
In plain terms: your AI models now use a fraction of the memory without getting dumber.
Before vs After
On a 16 GB machine:
- Before: Llama 3.2 1B + Whisper Base + TTS = barely fits, mediocre quality
- After: Llama 3.1 8B + Whisper Medium + TTS = runs comfortably, dramatically better output
On an 8 GB machine:
- Before: Could only run the 1B model alone
- After: Runs a 3B model + Whisper Base + TTS together
Full stack memory:
- Before: 35 GB for everything
- After: 15 GB for everything
What this means for editing
- Better AI commands "remove the intro" actually works now because Mistral 7B understands context far better than a 1B model
- Better transcription Whisper Medium fits where only Whisper Base could before, so captions are more accurate
- Longer content: Process hour-long podcast transcripts without running out of memory. The 6x KV cache reduction means 6x longer input context
One-click setup in Settings
We added a new AI Optimization panel in Settings. It auto-detects your hardware and recommends the best configuration:
- Performance Tier: Lite (4-8 GB), Standard (8-16 GB), or Pro (16-32 GB). Each tier is tagged with "Best for your hardware" based on your actual RAM.
- KV Cache Compression: Pick 4-bit (near-lossless), 3-bit (5x compression), or 2-bit (aggressive). Recommended level highlighted based on your system.
- Memory Budget: Set once, and the system optimizes everything to fit.

Would love to hear, what's your RAM situation, and does this make local AI editing viable for you?

Hey everyone!
We just shipped Smallest AI (Waves) integration into OpenCut-AI, and we're excited to share what this unlocks for creators.

What's new
OpenCut-AI now has three voice engines built in:
1. Local (Coqui XTTS) -- Runs entirely on your machine. 12 languages, voice cloning, zero API keys needed. Best for offline editing and privacy-first workflows.
2. Sarvam AI -- Purpose-built for Indian languages. 22 regional languages for transcription, 11 for text-to-speech, with 23+ natural speaker voices. If you're creating content in Hindi, Tamil, Telugu, Bengali, or any Indian language -- this is the best engine for you.
3. Smallest AI (NEW) -- Ultra-fast cloud TTS and STT. ~100ms latency, 80+ voices across 15 languages, and speech-to-text covering 39 languages with speaker diarization and emotion detection. This is our most versatile engine yet.
What you can do with Smallest AI
- Generate voiceovers in English, Hindi, Spanish, Tamil, and 11 more languages with natural-sounding voices
- Transcribe audio/video in 39 languages with automatic subtitle generation
- Control speech speed from 0.5x to 2.0x
- Pick from 80+ voices -- each language has multiple male and female options
- Process long content -- auto-chunking handles videos of any length
How it works
1. Grab a free API key from app.smallest.ai
2. Paste it in Settings > API Keys > Smallest AI
3. Select "Smallest AI" in the Voiceover or Captions panel
4. Generate
That's it. No server setup, no model downloads, no GPU required.
We're open to adding more models
This is the part we're most excited about. OpenCut-AI is built with a pluggable engine architecture. Adding a new voice or transcription provider is straightforward, and we want the community to drive what comes next.
Models we're considering:
- ElevenLabs (premium voice synthesis)
- Deepgram (real-time STT)
- Fish Speech (open-source voice cloning)
- Kokoro TTS (lightweight and fast)
- StyleTTS 2 (human-level quality)
Have a model you'd love to see? Drop it in the comments with:
- What it does
- Why it matters for video editing
- A link to their docs
We'll prioritize based on what the community wants most.
Links
- GitHub: github.com/Ekaanth/OpenCut-AI
- Smallest AI Docs: waves-docs.smallest.ai
- Get a Smallest AI key: app.smallest.ai
We'd love to hear what models and features you want next. Let us know!