🖥️ Desktop App · API-Based

v1.1.0

AutoFlowCut

Name: AutoFlowCut
Author: Touchizen

Prompts in, video project out

Connect your Google AI Studio API key once, bulk-generate AI images and videos with Gemini and Veo, then export complete CapCut projects with timeline, audio, subtitles, and animations.

📝 Connect API key → TXT/CSV/SRT input → Gemini images → Veo videos → CapCut export

Get it on Microsoft Store macOS Download Release Notes

🎬Video Demo

Watch How It Works

See the full workflow from importing prompts to exporting a complete CapCut project.

📸App Preview

See AutoFlowCut in Action

From prompt input to CapCut export — a seamless AI content creation workflow.

1 / 12

💻Download & Install

Download & Install

AutoFlowCut is a standalone desktop app. Download for your platform and start creating.

macOS

Download DMG from GitHub Releases. Supports Apple Silicon & Intel.

macOS

Windows

Available on Microsoft Store. Supports Windows 10/11.

Windows

System Requirements

Google AI Studio API key (for Gemini/Veo generation)

macOS 12+ or Windows 10+

Internet connection for AI generation

Release Notes — View version history on GitHub Releases

💡 What is AutoFlowCut?

What is AutoFlowCut?

AutoFlowCut is a desktop app for the full AI video pipeline: import prompts, generate images with Google Gemini API, generate T2V/I2V clips with Veo API, place audio and subtitles, then export everything as a ready-to-edit CapCut project. No web automation, no browser login loop, no reCAPTCHA interruptions.

100+

Batch Image Gen

T2V+I2V

AI Video Generation

1-Click

CapCut Export

Google API Powered

Direct Gemini & Veo API Workflow

Since v1.0.0, AutoFlowCut is fully API-based. It connects to Gemini and Veo through your Google AI Studio API key, skipping web automation, login popups, and reCAPTCHA interruptions while generating about 100 images in about 2-5 minutes.

🖼️

Image Generation

Create high-quality scene images through Gemini API with references and style presets. Around 100 images finish in about 2-5 minutes.

🎬

Video Generation

Generate Text-to-Video (T2V) and Image-to-Video (I2V) clips through Veo API.

🆓

Bring Your Own Key

Use your own Google AI Studio API key. Usage follows your Google quota and billing directly.

Get a Google AI Studio API key

🔄 Workflow

4-Step Automation Pipeline

📝

Enter Prompts

Enter your Google AI Studio API key, then write scene descriptions or import TXT/CSV/SRT files.

🖼️

Generate Images

Gemini API creates images with consistent style via references.

🎬

Generate Videos

Veo API creates T2V or I2V videos for selected scenes.

✂️

Export to CapCut

One click exports a complete CapCut project ready to edit.

TXT / CSV / SRT→Gemini API 🖼️→Veo T2V / I2V 🎬→CapCut ✂️

🎬 story-engine skill

9-Wave Story Production Pipeline

From idea to YouTube upload — the complete AI-powered workflow with story-engine skill

Story Design

🔍

Story Design

Analyze references and fact-check to identify patterns and strengths, then set the story direction. Branches between new production and rewrite.

Reference video / topicStory design + verified facts

📋

Synopsis + Preflight

Write a 20-chapter Setup–Rising–Climax–Resolution–Hook synopsis, then validate structure, foreshadowing, and suspense before writing.

Story designSynopsis + preflight checklist

Script Writing

✍️

W3User Confirmation

Script Writing + Review

Write the full screenplay in Setup → Rising → Climax → Resolution → Hook order; an AI subagent reviews and revises for up to 5 rounds.

SynopsisReviewed script

Production

📦

Production Extract

Extract narration lines, dialogue cues, and SFX markers from the finalized script.

Approved scriptNarration / dialogue / SFX list

🎙️

TTS & SFX Generation

Generate voice narration (ElevenLabs/Typecast) and sound effects, with timecode verification. Output as MP3 + SRT.

Narration / SFX listMP3 + SRT files

📊

Storyboard CSV

Create references.csv (characters/scenes) and scenes.csv (prompts + subtitles), reviewed via batch QA.

Script + SRTreferences.csv + scenes.csv

Visual & Upload

⚡

W7User ConfirmationAutoFlowCut

Image Production

AutoFlowCut batch-generates reference and scene images/videos from CSV and runs image QA.

CSV + referencesImages / videos

🎬

Assembly

SFX scene matching, audio import, and CapCut export — assembles an edit project with the Ken Burns effect applied.

Images / videos + audioCapCut project

🚀

Upload Info

Generate SEO-optimized title, description, tags, and thumbnail for YouTube upload.

Final contentUpload config JSON

🚦

Gate System

Each wave transition is enforced by the MCP gate system. Waves cannot be skipped. W3 (Script Writing + Review) and W7 (Image Production) require explicit user approval before proceeding.

Save Time

Hours of Work in Minutes

AutoFlowCut automates the entire content creation pipeline — from prompts to a ready-to-edit CapCut project.

❌

Manual Work

4+ hours

✅

With AutoFlowCut

about 2-5 min

100 images

about 2-5 min

Veo T2V+I2V

API video generation

1-Click

CapCut export

✨ Key Features

Key Features

🖼️

AI Image Generation

Batch generate 100+ images with Google Gemini API. Around 100 images finish in about 2-5 minutes, while reference tags keep characters, backgrounds, and styles consistent.

🎬

AI Video Generation

Generate videos from text prompts (T2V) or animate existing images (I2V) with Veo API. Choose the best result per scene for export.

✂️

One-Click CapCut Export

Export a complete CapCut project with timeline, media, audio, subtitles, and Ken Burns animations. Supports both image and video scenes.

🎯

Smart Media Selection

Choose between image, T2V video, or I2V video per scene. Duration auto-adjusts to match the selected media.

🔄

Audio Timeline

Import narration, dialogue, and SFX packages. Timecoded files are matched to scenes and placed on separate CapCut tracks.

🎬 AI Video Generation

AI Video Generation

Automatically generate videos from text or images with Veo API

📝

T2V — Text to Video

Generate videos directly from text prompts with Veo API. Describe your scene and receive a moving clip without relying on browser automation.

↓Input: Text prompt

↑Output: AI-generated video

★Use case: Concept videos, rapid prototyping, text-based storyboards

Text→Veo API→Video

🖼️

I2V — Image to Video

Transform your AI-generated images into animated videos with Veo API. Preserve the character, background, and style of the original image while adding natural motion.

↓Input: AI-generated image

↑Output: Animated video

★Use case: Image animation, character motion, background effects

Image→Veo API→Video

🎯

Smart Media Selection

Choose the best result per scene — image, T2V, or I2V. Default priority: I2V → T2V → Image. Your selection is automatically applied when exporting to CapCut.

I2V→T2V→Image

⚡ AutoFlowCut vs Whisk2CapCut

AutoFlowCut vs Whisk2CapCut

Built on the same foundation, now powered by official Google AI APIs

⚠️

Google Whisk was discontinued on April 30, 2026. Whisk2CapCut can no longer generate new images through Whisk. We recommend migrating to AutoFlowCut.

Feature	Whisk2CapCut	AutoFlowCutNEW
AI Engine	Google Whisk	Gemini + Veo API
Image Generation	✅	✅
Video Generation (T2V / I2V)	❌	✅ T2V + I2V
CapCut Export	✅	✅
Per-Scene Media Selection	❌	✅
Ken Burns	✅	✅

👥 Who Is This For?

Who Is This For?

🎭

Faceless YouTube Creators

Automate the entire AI image + video to CapCut pipeline for narration and slideshow channels.

📖

AI Story & Bedtime Story Channels

Keep character consistency with references, generate videos for key scenes, export everything to CapCut.

📱

Shorts, Reels & TikTok Creators

Quickly turn AI-generated scenes into short-form video projects with mixed image and video content.

🎓

Educators & Course Creators

Turn scripts or subtitles into illustrated video lessons with AI images and animated video scenes.

🚀 Detailed How-To

Complete in 5 Steps

📝

Enter Prompts & Set References

Import scene prompts from TXT, CSV, SRT files and match character/background/style references by tags.

🖼️

Batch Generate AI Images

The Gemini API auto-generates 100+ images with consistent style using references. Auto-retry on errors included.

🎬

Generate AI Videos (T2V / I2V)

Use the Veo API to generate Text-to-Video (T2V) or Image-to-Video (I2V) for selected scenes. Choose the optimal media per scene.

🎯

Select Media & Edit Scenes

Select export media from image, T2V, I2V in the scene list. Duration auto-adjusts and subtitles are editable.

✂️

Export CapCut Project

One click exports a complete CapCut project with timeline, media, subtitles, and Ken Burns animations. Start editing immediately!

📂Input Formats

Flexible Input Options

Import your content from multiple formats. Each format is automatically parsed into scenes.

📝Text Prompts

One prompt per line. The simplest way to get started.

A young scholar reading under a pine tree, Joseon era
A merchant crossing a stone bridge at dawn
Two warriors facing each other in a bamboo forest

📊Scene CSV

Structured data with columns: prompt, subtitle, characters, scene_tag, style_tag, duration.

prompt,subtitle,characters,scene_tag,duration
"Scholar reading under pine","한 선비가 소나무 아래서...",scholar,reading_scene,5

💬SRT Subtitles

Standard subtitle format with timing. Auto-converts to scenes with start/end times.

1
00:00:00,000 --> 00:00:05,000
한 선비가 소나무 아래에서 책을 읽고 있었다.

🧠Generate with AI

Use Claude, ChatGPT, or Gemini to generate scene data from your story.

Write your story or script

Use the AI prompt template below

Copy the generated CSV

Import into AutoFlowCut

📖View CSV/SRT file format guide→

🟠

Claude

🟢

ChatGPT

🔵

Gemini

✂️CapCut Export

Export to CapCut

One-click export to a fully structured CapCut desktop project.

📁

Project Structure

Timeline with images/videos, subtitles, and Ken Burns animations.

🔍

Ken Burns Effect

Auto zoom & pan animations for static images. Pattern or random mode.

💬

SRT Subtitles

Subtitles are embedded in the timeline with proper timing.

🎬

Media Files

All generated images and videos are included in the project.

🎬Ken Burns Effect

Automatically applies zoom and pan animations to image clips, bringing static images to life. Does not apply to video clips.

Without Effect

Static image

Zoom In

Dynamic motion

Ken Burns effect adds natural camera movement to static images, bringing your video to life. Automatically applied when exporting to CapCut.

🎯Pattern Mode

Cycles through 10 predefined patterns

🎲Random Mode

Generates random zoom/pan values each cycle

📁CapCut Project Folder

🍎

macOS

~/Movies/CapCut/User Data/Projects/com.lveditor.draft/

🪟

Windows

%USERPROFILE%\AppData\Local\CapCut\User Data\Projects\com.lveditor.draft\

📥Import to CapCut

Export project from AutoFlowCut

Copy to CapCut project folder

Open CapCut desktop — project appears automatically

Edit timeline, add effects, and render

📖View Full Guide→

📂Output Structure

project_name/
├── draft_info.json
├── draft_meta_info.json
├── media/
│   ├── scene_001.png
│   ├── scene_002.mp4
│   └── ...
└── README.txt

🗒️ Release Notes

Version History

The latest version gets the detail; older releases stay compact until you need the full history.

Current version

v1.1.0 - Faster batches and cleaner prompt handling

View all on GitHub Releases

v1.1.0 focuses on more predictable batch generation, updated image defaults, and smoother Korean prompt editing with reference mentions.

100 images in about 2-5 minutes

The API-based image pipeline and batch queue improvements keep 100-image generation in the about 2-5 minute range.

Nano Banana 2 by default

The default image model now uses Nano Banana 2 on gemini-3.1-flash-image, with the main-process default kept in sync.

Separate image/video concurrency

Image and Veo video concurrency can be tuned independently, with video generation using a sliding window and a default of 4 jobs.

Random waits removed

The old 7-15 second random delay has been replaced with settings-based queue execution for clearer long-batch behavior.

Veo stability fixes

Polling guards, NaN concurrency checks, and authentication error counting were tightened for safer failure handling.

Korean @mention particles

Korean particles such as eun/neun/i/ga are split automatically after @mentions, so reference-image prompts stay natural.

Supported Previous Releases

Only downloadable API-based 1.x releases are shown in the default list.

v1.0.1

Reference prompts and media previews

@mentions attach reference images inside prompts, with better video preview behavior and corrected I2V restore routing.

v1.0.0

First public Gemini/Veo API release

The first stable release after the full move from Google Flow web automation to API-based generation, reaching about 100 images in about 2-5 minutes.

Legacy History and Removed Binaries

v0.9.15 and earlier used the Google Flow web workflow, so those binaries are no longer provided.

Show legacy history

Legacy binaries were removed

v0.9.15 and earlier

Earlier versions depended on the Google Flow web workflow.
Because Google Flow access is now blocked or changed, those binaries were removed.
For new installs or reinstalls, use v1.0.0 or later with the Gemini/Veo API workflow.

Reference image hotfix

v0.9.14

Reference images are sent through imageInputs[] in Flow requests
Response matching handles both supported formats more reliably

SRT/CSV track separation and subtitle reliability

v0.9.13

Dedicated SRT track model separated from CSV scene data
Stronger SRT re-import, MCP update, and CapCut subtitle export paths
Video poster thumbnails and lazy loading improved preview performance

SRT/Text/CSV sequential import improvements

v0.9.12

Sequential file imports preserve existing fields across merges
SRT story input and CSV editing workflows were connected more flexibly

Simple Pricing

Free forever, upgrade only when you need more

Free

5 exports per month + 5 signup-bonus exports

5 CapCut exports per month (auto-renews on the 1st)
+5 lifetime bonus exports on signup
All basic features

Start Free

POPULAR

Pro

For serious creators

$9.99/mo

or $99.99/yrSave 17%

Unlimited exports
Ken Burns effects
Priority support

Go Pro

Purchase and subscription are handled inside the app — available in both the Desktop app and Chrome extension.

Feature Comparison

Feature	Free $0	Pro (Monthly) $9.99/mo	Pro (Yearly) $99.99/yr 17% OFF
Gemini/Veo API Image & Video Generation	BYO API key	BYO API key	BYO API key
CapCut Export	5/month + 5 bonus	Unlimited	Unlimited
T2V / I2V Video Generation
Ken Burns Effect + Auto Subtitle
Priority Support
Price	$0 Free forever	$9.99 /month	$99.99 /year $8.33/month (17% OFF)

Trust & Safety

Safe & Transparent

AutoFlowCut is designed with privacy and transparency as core values.

Privacy & Safety

Google AI Powered

Uses official Gemini and Veo APIs through your Google AI Studio key. No automation of private web sessions.

Local Processing

Your projects and exports stay on your device. AI generation requests go directly to Google using your own API key.

Version Transparency

Release notes and download availability are documented on GitHub Releases.

Transparent Pricing

The app is free to download. CapCut export Pro is optional; Google API usage is billed by Google.

Trust Badges

Local Projects

Projects and exports stay on your device

Release History

Release notes and download status documented

Transparent Pricing

Free app, Google API billed directly

💬 FAQ

Frequently Asked Questions

Everything you need to know about AutoFlowCut

QWhat AI model does AutoFlowCut use?

AutoFlowCut uses Google Gemini API for image generation and Veo API for video generation. You bring your own Google AI Studio API key, and generation requests go directly from the app to Google.

QHow is it different from Whisk2CapCut?

Whisk2CapCut used Google Whisk and browser automation for image-first workflows. AutoFlowCut uses official Gemini/Veo APIs, supports T2V and I2V video generation, adds audio timeline support, and exports complete CapCut projects.

QDo I need a Google API key?

Yes. Create a Google AI Studio API key, paste it into AutoFlowCut once, and the app calls Gemini and Veo directly. No Google browser session or reCAPTCHA flow is required inside the app.

QWhat file formats are supported for input?

You can import scene prompts from TXT (one per line), CSV (structured data with columns), and SRT (subtitle files with timing). Each format is automatically parsed into scenes.

QIs the CapCut project compatible with CapCut desktop?

Yes, the exported project is fully compatible with CapCut desktop. It includes timeline, media files, subtitles, and Ken Burns animations — ready to edit immediately.

QIs AutoFlowCut free?

AutoFlowCut is free to download. CapCut export has a free monthly allowance and an optional Pro plan for unlimited exports. Gemini/Veo API usage is billed directly by Google according to your own API key and quota.