overcrank Request API key

Live benchmark29,676 frames rendering behind this page

Render faster than the film plays.

Overcrank is on-demand cloud GPU rendering for videos built in code and Blender. Our engine is 33× faster on a single GPU — and because the cloud fans out across parallel GPUs for virtually the same cost, a 16-minute film that takes headless Chrome, Remotion, or HyperFrames 36 minutes comes back in under 20 seconds.

Full timeline163 × 183

29,676 frames at once.

Browser-based video tools step through your animation one screenshot at a time. Because a scripted video's timeline is already known up front, Overcrank computes motion across the entire film in advance and composites frames in parallel on the GPU.

Direct to NVENC1080p & 4K

Every frame painted and encoded in VRAM.

Static HTML/CSS layers rasterize once, 3D scenes render headlessly over Vulkan, and finished frames go straight from GPU memory into hardware video encoders with audio mixed in.

Automatic verificationPixel-checked

Verified against real Chrome.

Overcrank automatically spot-checks rendered scenes against headless Chrome. If any scene uses a browser feature outside the GPU fast path, Chrome renders just that scene so your final MP4 never breaks.

Benchmarks16.5-minute 1080p film · 103 scenes · 29,676 frames

36 minutes drops to 17 seconds. 33× faster on one GPU — over 120× fanned out for the same pennies.

Browser RenderChrome · Remotion / HyperFrames (16 CPUs)
36 min
Overcrank · 1× GPUSingle L40S or local RTX card · ~6¢
~65 s
Overcrank · 8× CloudDefault parallel GPU fan-out · ~9¢
~17 s

Bars are drawn to exact linear scale for a 16.5-minute 1080p film (29,676 frames at 30 fps).

~17s

Default 8× GPU cloud burst

Splits your film at scene cuts across 8 GPUs in parallel and stitches closed H.264 GOPs with zero re-encoding.

125×

Faster than headless Chrome

Already 33× faster on a single machine (~65 s on one L40S or local RTX GPU) before multi-GPU fan-out even starts.

~6–9¢

Same pennies, 4× less wait

8 GPUs running for 17 seconds use nearly the exact same GPU-seconds as 1 GPU running for 65 seconds.

9.5s

4K Blender preview loop

Preview a 12-second 4K Blender shot faster than playback on a warm GPU pool, or fan out full Cycles across 10 GPUs.

Benchmark details: Single-GPU Overcrank runs take 62–81 s (~65 s median) inside 1× warm NVIDIA L40S; 8× GPU parallel fan-out (~17 s active GPU wall time) partitions scenes across 8 L40S workers with parallel audio mix and lossless IDR stream-copy muxing (cold GPU spin-up adds a few seconds unless pre-warmed with overcrank warm). Browser baseline is hyperframes render (headless Chrome) on 16 CPU cores (2,146 s). Visual fidelity across 392 sampled frames: 38.39 dB median PSNR, zero frames flagged.

Built for AI agentsClaude Code · Cursor · Codex · Windsurf

One prompt gives your agent a cloud GPU studio. Paste it in, drop an API key, and iterate at film speed.

Copy & paste into your coding agent
Set up Overcrank so you can render our video and Blender projects on cloud GPUs:

1. Install the CLI + MCP server: `pip install "overcrank[mcp]"`
2. Run `overcrank llms` and save its rules as a skill so you know how to estimate costs, run fast previews, and verify renders.
3. Register `{"mcpServers": {"overcrank": {"command": "overcrank", "args": ["mcp"]}}}` in your MCP config.
4. Ask me for my Overcrank endpoint and API key (`overcrank config set endpoint https://api.overcrank.cloud` and `overcrank config set token`).

Whenever we edit an HTML/CSS/GSAP scene or a `.blend` file:
- Call `warm_up()` when you start editing so a GPU is hot before we export.
- Quote cost first, render a fast 5-second or preview-quality clip so we can inspect frames immediately, then render the full verified MP4 with `--max-cost`.

Works with any MCP-compatible agent or plain shell access. No local NVIDIA GPU, CUDA toolkit, or Blender install needed on your laptop.

01

Instant edit → watch → fix loops

Agents write GSAP timelines or tweak Blender lighting, render a preview in ~10 seconds, inspect dumped PNG frames, and fix layout or lighting issues autonomously.

02

Hard spending caps built in

Every render supports --estimate before uploading a single byte and --max-cost to halt automatically if a job ever exceeds your budget.

03

Content-addressed delta uploads

Change one caption or camera keyframe and only the modified file uploads. Unchanged assets and Chrome verification results stay cached.

overcrank cli
# 1. quote time & cost before uploading
$ overcrank render ./my-video --estimate

# 2. fast 5-second draft while iterating
$ overcrank render ./my-video --seconds 5 --fallback never -o look.mp4

# 3. full Chrome-verified export, capped at $0.50
$ overcrank render ./my-video --max-cost 0.50 -o final.mp4

Interactive estimatorgrounded in logged GPU runs

See what your render takes. Pick your format, duration, and resolution.

16 min 30 s · 29,700 frames
Overcrank wall time ~17 s
Estimated compute ~$0.09
Speed advantage 126× faster
Overcrank Cloud (8× GPU Fan-Out) 17 s
Headless Browser (Chrome / Remotion / HyperFrames) 35 min 49 s

Default 8× GPU fan-out splits scenes in parallel and stitches closed GOPs with zero re-encoding. $0.00 when idle.

Supported Pipelinesweb · 3d · blender

Render the formats agents already write. No proprietary DSL required.

Web Video

HTML, CSS, JavaScript & GSAP

Built for programmatic motion graphics, HyperFrames projects, and Remotion-style agent workflows. Landscape 16:9, vertical 9:16 Shorts/Reels, or custom dimensions with multi-track audio and video layers.

  • GSAP 3.14
  • HyperFrames
  • HTML / CSS / SVG
  • Chrome Verification

Real-Time & Ray-Traced 3D

Three.js & ThreeRT

Drop Three.js WebGPU scenes right between crisp HTML typography layers on a shared timeline, or switch to hardware ray-traced global illumination (ThreeRT) when shots call for real bounce light and soft shadows.

  • Three.js WebGPU
  • Headless Vulkan
  • ThreeRT HW Ray Tracing

3D Film

Blender Cycles (.blend) — with live warm previews

Point Overcrank at a .blend file and get an MP4 straight from Cycles on datacenter GPUs. Warm background Blender pools reload scene edits in place so 4K lighting and camera previews come back faster than the clip plays. At full sample counts, fan out shots across multiple GPUs.

55-second 4K Cycles benchmark (1,329 frames)
Quality preset1× L40S10× L40S
preview (sub-realtime)38 s—
fast (36.4 dB)3 min 15 s31 s
full (37.8 dB)8 min 39 s61 s

Architecture33× per GPU · 125× fanned out

33× faster on one machine. Over 120× across eight — for the same pennies.

  1. 01

    Solve motion up front

    A web browser recalculates style, layout, and paint 30 to 60 times every second. Overcrank evaluates your entire animation timeline once up front into compact per-frame transform matrices.

  2. 02

    Paint each layer once

    Each static text block, card, SVG, or image layer is laid out and rasterized once by a native Rust HTML/CSS engine instead of being redrawn thousands of times.

  3. 03

    Fan out & encode in VRAM

    GPU kernels composite frame batches straight into hardware NVENC encoders — flying on a single local RTX card, or fanning out at scene boundaries across 8 cloud GPUs with lossless IDR stream stitching for the same compute cost.

  4. 04

    Spot-check with Chrome

    Key frames from every scene are automatically compared against headless Chrome. Any scene using unsupported CSS or custom canvas scripts seamlessly falls back to Chrome.

Private Previewcurrent coverage

Production-fast today, with automatic Chrome fallback where needed.

GSAP & structured web scenes
Across 29 production multi-scene films (over 600 scenes), Overcrank renders nearly every scene natively on the GPU, with 99.9%+ of sampled frames matching headless Chrome and automatic Chrome fallback catching edge cases.
Arbitrary third-party web code
Scenes that rely on unsupported JS animation libraries, live 2D canvas drawing, or complex CSS blend filters automatically fall back to headless Chrome per scene — rendering accurately at standard browser speed while GPU-compatible scenes stay fast.
Isolated multi-tenant sandboxes
Every render runs in an ephemeral, network-jailed sandbox with per-key rate limits, cost ceilings, and zero shared state between users.
Early access
Self-serve billing is in progress. We are onboarding early developers and AI agent builders directly with private API keys — email founder@overcrank.cloud to get a key.

Since you opened this page00:00

The film behind this page is still rendering.

Headless Chrome is on frame 0 of 29,676.