IDOCInTheBox IDOCInTheBox v6.0
★ Early Adopter Special — First 50 Copies Only

Restore your memories.
20 AI engines.
One app.

Advanced Tape Restorer v6.0 is the most powerful Windows application for rescuing VHS, Hi8, 8mm, Betamax, and DV tapes — with a 20-engine AI suite covering upscaling, interpolation, face restoration, colorization, audio enhancement, damage repair, and more.

20AI Engines
12UI Pages
4KMax Output
VMAFQuality Score
Win 10/11Native App
Step 1 — Download Free
Download Installer (v6.0.0)
Step 2 — License Key
$49.95$150
Early adopter price. Auto-increases after sale #50.
Purchase License Key — $49.95
  • Lifetime license — all v6.x updates included
  • Instant key delivery via email
  • Priority email support
  • One-time purchase, no subscription
  • Windows 10 & 11 native app
Restoration Pipeline

Analog in. Stunning digital out.

Every tape runs through a multi-stage professional pipeline — each engine layering on the last for maximum quality.

Step 1
📼
Import / Capture
VHS, Hi8, 8mm, DV — file or live capture
Step 2
🔬
Auto Analysis
VMAF, PSNR, SSIM, scene detect, field order
Step 3
⚙️
QTGMC Deinterlace
7 presets, motion-compensated
Step 4
🧹
Filter Suite
BM3D denoise, TComb, Bifrost, sharpening
Step 5
🤖
20 AI Engines
Upscale, interpolate, inpaint, colorize, faces
Step 6
🎬
Export
H.265, ProRes, DNxHD, AV1, 4K, HW accel
Maximum Quality Pipeline — All Stages Active
720×480i Input QTGMC 60fps BM3D Denoise ProPainter Repair RFDA Artifact Fix RIFE 2× Interp RealESRGAN 4K GFPGAN Faces LavaSR Audio 3840×2160 @ 60fps
AI Engine Suite

20 purpose-built AI engines

From SD-to-4K upscaling and frame interpolation to B&W colorization, face restoration, audio enhancement, and tape artifact repair — every restoration challenge has a dedicated engine.

RealESRGAN 4x
Upscaling
64 MB · 4× super-resolution
BasicVSR++ 2x
Upscaling
37 MB · temporal awareness
SwinIR 2–4x
Upscaling
48 MB · transformer-based
ZNEDI3 2x
Upscaling
No download · VapourSynth native
NVIDIA VFX AI
Upscale / Denoise / Deblur
Requires NVIDIA® VFX SDK · RTX GPU
RIFE 2–4x
Interpolation
17 MB · scene-aware
DAIN
Interpolation
Depth-aware frame generation
FILM
Interpolation
By Google Research · Apache-2.0
FLAVR
Interpolation
Flow-agnostic multi-frame
Video Swin-UNet
Tape Restoration
200 MB · analog-specialized
SeedVR2
Restoration
Tiling · DiT block offloading
Restormer
Deblur / Denoise
CVPR 2022 · progressive tiling
ProPainter
Inpainting
280 MB · scratch repair · user-installed
VideoCleaner
Forensic
External tool · user-installed
DarkIR
Tape Artifacts
Low-light / IR · FP16/FP32
BiT
Tape Artifacts
Analog tape noise
RFDA
Compression Artifacts
MPEG-2 / DV · QP selection
GFPGAN v1.4
Face Restoration
350 MB · built-in
CodeFormer
Face Restoration
Fidelity slider · user-installed · non-commercial license¹
DeOldify
Colorization
120 MB · B&W → color
LavaSR v2
Audio Enhancement
16kHz → 48kHz broadband
Echoes Over Time
Audio Enhancement
VoiceFixer · dry/wet mix

4 Inference Modes — Auto-Selected Based on Your Hardware

ATR automatically picks the fastest available backend — or you can override per-engine.

PyTorch Native
CUDA / ROCm
Full NVIDIA® CUDA® 11.8+ and AMD ROCm GPU acceleration. Best for RTX™ 3060+ and RX 6000/7000 series cards.
🚀
TorchScript / JIT
20–30% faster
JIT-compiled and cached models give a 20–30% speed boost over PyTorch native with identical quality output.
🔷
ONNX + DirectML
40× vs CPU
Runs on Intel Core Ultra NPUs, AMD Ryzen AI, and any DirectX 12 GPU. FP16/INT8 quantization supported.
🎯
NVIDIA® VFX / TensorRT™
RTX exclusive
TensorRT-accelerated upscale, denoise, and deblur chained in a single decode/encode pass — no VapourSynth overhead. Requires NVIDIA VFX SDK (separate download).
VapourSynth Filter Suite

Professional filters. Zero command lines.

Built on VapourSynth — the professional video processing framework. Every filter is tunable from the GUI, with live preview so you can see results before committing a full render.

Deinterlacing

  • QTGMC — 7 quality presets (Draft → Placebo)
  • Auto field order detection (TFF / BFF / Progressive)
  • Standard 30fps or Bob 60fps deinterlace

Denoising

  • BM3D — GPU-accelerated temporal-spatial
  • FFT3D — frequency-domain filtering
  • NLMeans / hqdn3d patch-based
  • MCTemporalDenoise motion-compensated
  • Chroma denoise — Light / Medium / Heavy

VHS Artifact Removal

  • TComb — dot crawl & color separation
  • Bifrost — advanced chroma correction
  • Tracking error correction (3 modes)
  • Chroma shift XY correction

Color & Tone

  • Auto white balance
  • Manual level adjustment with histogram
  • Brightness / contrast / saturation
  • Theatre / anamorphic correction (VHS, LaserDisc presets)

Sharpening & Enhancement

  • UnsharpMask — traditional edge enhance
  • LSFmod — adaptive with edge protection
  • Dehalo — directional halo reduction
  • Debanding (f3kdb) — banding removal

Additional Filters

  • Grain synthesis — size, strength, constant
  • Temporal smoothing — reduces flicker
  • DePan stabilization (MEstimate auto)
  • Resize / crop — Lanczos, Cubic, Bicubic
AI Audio Enhancement

Restore the voices, not just the picture.

Tape audio degrades along with video — muffled frequencies, hiss, and degraded speech. ATR v6.0 includes two dedicated AI audio engines plus a chain mode that combines both.

🎙️

LavaSR v2 — Broadband Speech Restoration

Upsamples degraded 16kHz tape audio to full 48kHz broadband using a HuggingFace AI model. Includes a built-in denoising toggle to remove tape hiss before expansion. Runs on CUDA, CPU, or DirectML.

Audio AI
🔊

Echoes Over Time — VoiceFixer Speech Refinement

VoiceFixer-based speech restoration with a dry/wet mix slider (0.0–1.0) so you control how aggressively the AI reshapes the audio. Ideal for interviews, family conversations, and narration on old tapes.

Audio AI
⛓️

Chain Mode — Two-Stage Enhancement

LavaSR cleans up broadband quality first, then Echoes Over Time refines speech clarity in a second pass. One-click selection in the engine dropdown. Automatic audio detection skips enhancement when no audio stream is found.

Audio AI
Speaker Matching

Resemblyzer-based 256-d d-vector speaker embedding lets you identify and match speakers across segments of your restored audio. Gracefully skips when Resemblyzer is not installed.

Face Restoration & Colorization

Bring every face — and every color — back to life.

ATR v6.0 goes beyond traditional restoration with AI-powered face enhancement and automatic colorization of black & white footage.

👤

GFPGAN v1.4 & CodeFormer — Face Restoration

Built-in GFPGAN v1.4 (350 MB, Apache-2.0) detects and enhances faces automatically. CodeFormer is available as a user-installed alternative (S-Lab non-commercial license¹) with an adjustable fidelity slider for fine-tuned control between realism and sharpness. Both support adjustable detection threshold and separate background enhancement.

Face AI
☁️

Face Reference Library — Cloud Photo Import

Build a personal face identity library from your own photos — imported from local files, iCloud® Photos, Google Photos™ (Takeout), or Amazon Photos desktop. ATR auto-detects your iCloud sync folder, clusters faces with scikit-learn, and matches against tape footage using an adjustable similarity threshold (0.40–0.80). All processing is fully local — photos are never uploaded.

Face Reference
🎨

DeOldify — Black & White to Color

Automatically detects black & white footage and colorizes it using DeOldify's 120 MB AI model. An artistic factor slider (0–35) controls colorization style from conservative to vivid. Choose between Stable video and Artistic models.

Colorization AI
🔧

ProPainter — Scratch & Damage Inpainting

Uses temporal context from 10+ surrounding frames to reconstruct exactly what should be in a damaged area — removing scratches, mold spots, dropouts, tracking errors, date stamps, and watermarks. Three modes: Remove Artifacts (auto), Object Removal, and Restore Damaged Areas. (Requires separate installation — Apache-2.0 license.)

Inpainting AI
Quality Analysis

Measure, compare, and prove your restoration quality.

ATR v6.0 includes professional-grade video quality metrics — the same standards used by Netflix, broadcasters, and streaming platforms — with per-frame CSV and PNG export.

VMAF
Netflix perceptual quality metric — the gold standard for streaming
PSNR
Peak Signal-to-Noise Ratio — measures noise floor improvement
SSIM
Structural Similarity — captures texture and edge fidelity
MSE
Mean Squared Error — pixel-level reconstruction accuracy
VIF
Visual Information Fidelity — human visual system model
📊

Per-Frame Scoring & CSV Export

Every metric is computed per-frame and exported to CSV and PNG graphs — so you can pinpoint exactly which frames in your tape had the worst damage and verify your restoration improved them.

Analysis
🎬

Scene Detection

Automatic shot boundary detection with adjustable threshold and minimum scene length filters. Supports multiple detection algorithms to handle tape sources with inconsistent cuts.

Analysis
📄

HTML Analysis Reports

Generate detailed HTML quality reports covering resolution, framerate, codec, interlace pattern, field order, scene list, and all quality metrics — shareable with clients or archivists.

Analysis
Hardware Capture

Capture and restore in one app.

ATR v6.0 includes a full hardware capture module — no third-party capture software needed. Auto-detect your capture card, digitize your tape losslessly, then restore — all without leaving the app.

📡

Analog Capture — VHS, Hi8, Betamax & More

DirectShow-based capture for USB and PCI analog capture cards. Supports Composite, S-Video, and Component input. Configurable for NTSC (720×480 @ 29.97fps) or PAL (720×576 @ 25fps). Lossless codecs: HuffYUV, Lagarith, FFV1, UT Video.

Built-in
🔌

DV / miniDV — FireWire Native Stream Copy

Captures DV and miniDV tapes via FireWire (IEEE 1394) with native stream copy mode — preserving the original DV encoding with minimal loss. Supports miniDV, HDV, DVCAM, and DVCPRO. Timecode extraction included.

Built-in
🔍

Auto Device Detection

Automatically enumerates all connected DirectShow devices, classifies them as analog or DV, and displays them in a dropdown — no manual driver configuration required. Supports multi-device setups.

Capture
Scene Editor & Batch Workflow

Edit, compare, queue, and schedule.

ATR v6.0 is a full restoration suite — not just a processor. The built-in scene editor, timeline tools, and batch scheduler handle your entire archive workflow.

✂️

Scene Editor — Split-Screen Before/After

Real-time split-screen comparison with an adjustable divider between original and processed. Frame-by-frame navigation, zoom control, scene creation/merging/splitting, and synchronized timeline playback. Quickly verify every frame before final export.

Scene Editor
⏱️

Timeline In/Out Markers

Set precise start and end points with I/O keyboard shortcuts or draggable handles. Process only a portion of your tape — with a right-click context menu, focus-aware key handling, minimum gap enforcement, and exact audio/video trim sync via FFmpeg -ss/-to.

Timeline
📦

Batch Processing with Email Notifications

Queue unlimited jobs, apply presets to the entire batch, and monitor per-job ETA in real time. Schedule a delayed batch start for overnight processing. SMTP email notifications on completion and individual job errors — with one-click test from Settings.

Batch
🔌

Community Plugin System

Three pipeline hook points — pre_filter, post_filter, and post_encode — let community plugins inject custom per-frame processing. Plugins auto-discovered from %LOCALAPPDATA%, with dynamically generated settings UI, drag-to-reorder, cancel support, and skip-on-failure safety.

Plugins

12 Built-In Presets — Plus Unlimited Custom Presets

One click to apply a full restoration configuration. Save your own and share with others.

Basic Tape Restore (No AI)
Max Restore
Digitized Film
Tape: SWIN + 4x Upscale
Tape: SWIN + Chroma + 4x
Tape: SWIN + 4x + Smooth Motion
Tape: SWIN + Faces + 4x
DarkIR Test
SeedTest (SeedVR2)
DeOldify Colorization
SwinIR + RIFE
+ Your Custom Presets
🎵 Integrated Music Library

Search royalty-free music via Jamendo (Creative Commons), generate custom music from text prompts via ElevenLabs AI, or run fully local AI music generation with ACE-Step 1.5. Download to your local library, preview in-app, and add audio to your restored videos — all without leaving ATR.

Format & Codec Support

Every tape format. Every professional codec.

Tape Input Formats

  • VHS & S-VHS
  • Hi8 & Video8 (8mm)
  • Betamax & Betacam
  • DV, miniDV, HDV
  • DVCAM & DVCPRO

Output Video Codecs

  • H.265 / HEVC — CPU, NVENC, AMF, QSV
  • H.264 / AVC — CPU, NVENC, AMF, QSV
  • AV1 — libaom
  • ProRes — Proxy, LT, HQ, 4444, RAW
  • DNxHD / DNxHR
  • FFV1 — lossless archival

Output Audio Codecs

  • AAC, AC3, EAC3
  • FLAC — lossless
  • Opus — modern lossy
  • Copy — pass-through

Capture Codecs (Lossless)

  • HuffYUV
  • Lagarith
  • UT Video
  • FFV1
  • Native DV stream copy

Output Containers

  • MP4, MKV, MOV, AVI
  • Frame sequences (PNG / JPEG)
  • Video + frames simultaneously

Hardware Accelerated Encoding

  • NVIDIA® NVENC (H.264 / H.265)
  • AMD AMF (H.264 / H.265)
  • Intel Quick Sync (H.264 / H.265)
  • Auto-detection of available encoders
Pricing

Simple. One-time. No subscriptions.

Buy once and own it forever. Your license covers all v6.x updates — including every new AI engine added during the v6.x lifecycle.

Standard

$150
One-time purchase • Regular price
  • Lifetime license — Advanced Tape Restorer v6.x
  • Access to all 20+ AI engines*
  • All features identical to Early Adopter tier
  • Instant license key delivery via email
  • Email support
  • All v6.x updates — free
Buy at Standard Price
System Requirements

What you need to get started

Minimum
  • Windows 10 or 11 (64-bit)
  • 8 GB RAM
  • 2 GB VRAM (any DirectX 11 GPU)
  • 10 GB free disk space (SSD recommended)
  • FFmpeg 6.0+ (installer included)
  • VapourSynth R65+ (installer included)
Recommended (AI Features)
  • Windows 11 (64-bit)
  • 16–32 GB RAM
  • NVIDIA® RTX™ 2060+ — 8 GB+ VRAM
  • CUDA® 11.8+ for RIFE, RealESRGAN
  • RTX GPU for ProPainter (8 GB+ VRAM)
  • NVMe SSD for batch processing
AMD / Intel GPU
  • AMD Radeon RX 6000 / 7000 (ROCm)
  • Intel Core Ultra with NPU (DirectML)
  • ONNX Runtime DirectML — 40× vs CPU
  • Intel Quick Sync for hardware encoding
  • Some AI engines require NVIDIA CUDA
For Hardware Capture
  • DirectShow analog capture card
  • FireWire / IEEE 1394 card for DV
  • Fast storage for lossless capture
  • VCR, camcorder, or tape deck
  • RCA or S-Video cables
Support

We're here to help

📧

Email Support

Contact [email protected]. Include your Order ID from Gumroad for fastest response.

🔑

License Delivery

Keys are delivered automatically by Gumroad to your purchase email. Check spam first — then contact us with your Order ID.

📥

Verify Your Download

Always verify with the SHA256 checksum to confirm a safe, untampered installer.

📖

Documentation

Full product manual, quick start guide, capture guide, plugin development guide, and AI feature guides included with the app.