v0.3 · Early access · Windows desktop · by SYNAP LLC

Every AI model.
One infinite canvas.

promptGOAT is a native desktop studio that turns 22 hosted image, video, audio and LLM backends — plus your local ComfyUI — into a single visual workflow. Prompt it, generate it, edit it, stitch it, and track every cent it cost.

ONE-TIME FEE · LIFETIME LICENSE · BRING YOUR OWN KEYS

0AI backends
0+Story structures
0Keyframable effects
0Middlemen on your keys

One generate button. Every model you already use.

The studio at a glance

Everything happens on the board.

Nine systems, one canvas. Each one is summarized here — and broken down in full detail in the deep dive below.

22-backend generation

Image, video, audio, music, TTS and LLM services behind one Generate button — with queue lanes, progress, auto-generate loops and crash-safe recovery.

Local ComfyUI, tamed

Drop in any workflow — promptGOAT flattens subgraphs, builds a settings panel on the card, randomizes seeds, binds reference images and streams live progress.

The infinite board

Media, prompt, note, model and folder cards on a zoomable canvas with full undo, grid snap, alignment tools — your whole project in one spatial view.

A prompt engine, not a prompt box

Presets in weighted categories — 7 weight tiers, locks, excludes, favorites — assembled live by the composer. Three pick modes turn one setup into a thousand coherent variations.

The vault

Watch folders sync live into a searchable media library that reads the prompt, seed and model out of every render — and files stay safe to move even while they're on a board.

Built-in media editor

Crop, trim, overlays and 40 keyframable effects with easing and presets — plus collage, stitch, weave, Ken Burns and crash zoom — all rendered in the background, pixel-identical to the preview.

The Preset Exchange

Browse, install and publish community preset packs — voted on, human-moderated, integrity-checked twice, with donations that go straight to the author.

Storyboard script builder

Pick one of 106 narrative structures across 11 categories, cast a 36-field character sheet, and let any LLM — or your own pen — fill a beat map that lands on the board as shot cards.

Cost & energy tracking

Every generation logged locally with prompt, settings, tokens, cost and energy — plus spend caps that stop a runaway loop before the job is even sent.

The cards

This is what your board is made of.

Faithful to the app: a prompt is a card, a model is a card, a folder is a card — and a generation lands as a card next to the cards that made it, joined by a colored lineage border. Every card carries reference-slot badges, a lock, resize handles and full undo.

API MODELVEO 3.1 FAST
16:9
1080p
8 s
On
Client-spec ▾
ATTACHED
Randomize seed on Generate

API model card. Each hosted model exposes its real settings — aspect, resolution, duration, audio, format — right on the card, with color-coded reference slots, savable per-card presets and one Generate button. ComfyUI workflows get the same card with their own analyzed settings panel.

VIDEO8.0 s · 1080p
Generated: 2026-07-13 · 46 s
Model: Veo 3.1 Fast · Cost: $0.46
Reference Log:
POSITIVE PROMPT

Slow tracking shot, rain-soaked neon market…

NEGATIVE PROMPT

blurry, watermark, text

Send to BoardCopy Path

Media card. Outputs carry their complete generation record — model, reference log, prompts, timing and cost — so any result can be reproduced weeks later. The teal lineage border matches the prompt card that made it: which prompt made this is answered by looking, not searching.

PROMPTSEQ 2/5
POSITIVE PROMPT

Low-angle hero shot at golden hour, 35mm anamorphic, volumetric haze, film grain…

NEGATIVE PROMPT

oversaturated, deformed hands, watermark

Prompt card. A fragment of prompt, not "the prompt": cards assigned to a slot join top-card-first, in stacking order — drag one above another and you've rewritten the sentence. Number them (SEQ 2/5) and the board fires a whole shot list in order, unattended.

COMPOSER

portrait of a weathered sea captain, dramatic rim light, Kodak Portra 400, 85mm shallow depth

★ lighting film stock lens + 17 categories
RANDOM · weighted
Every generation

Composer card. A live mirror of the preset engine's assembled prompt, color-coded by category — lighting gold, film stock blue, lens green — updating as you toggle chips. Set it to RANDOM and every generation rolls a fresh, weighted, still-on-brief variation.

FOLDER12 / 48
Increment
D:\refs\b-roll

Folder card. Points at a folder on disk and cycles through its images — fixed, increment or random. Assign it to a reference slot and every generation in a batch pulls the next reference automatically.

VAULT1,204 ITEMS
⌕  search: "neon market"
Newest First

Vault card. A live, searchable window into your media library, right on the board — full-text search, sort by newest/oldest/largest, thumbnail sizing, and drag any result straight into a reference slot.

NOTE

Shot 14 — swap to the low-noise LoRA pair, keep the harbour fog. Client loved take 3's palette; lock that grade preset before the next batch.

Note card. Plain text on the canvas — the thing you actually think in. Notes live next to the work they describe instead of in a doc nobody reopens.

FILE
WAV
vo_captain_take2.wav
2.4 MB · 00:19
Show in FolderAssign to Slot

File card. Any file on disk — name, size, type — pinned to the board. Move the file anywhere and the card follows it; delete it and the card cleans itself up. Nothing rots.

SECTION · ACT 1 — SETUP
PROMPT · SHOT 1
PROMPT · SHOT 2
CHARACTER · MARA
MEDIA · TAKE 3

Section box. A resizable, labelled container that groups cards visually — the Script Builder drops one per act when it exports a storyboard to the board.

Deep dive

Eight systems. Zero compromises.

The complete breakdown of what ships with your license. Pick a system — everything listed is in the app today, not on a roadmap.

Generation

One Generate button in front of 22 hosted backends and your local hardware. The app orchestrates the queue; you stay in the creative loop.

Image models

Google's Nano Banana family (Nano Banana, Nano Banana 2, Nano Banana Pro) plus Imagen 4 Ultra & Fast, OpenAI GPT Image 2 / 1.5 / 1 / Mini, Kling Image v1.5 through v3 and o1, and Topaz upscaling & restoration.

Video models

Google Veo 3.1 (Standard / Fast / Lite), Kling v2.6 / v3 / v3-omni / video-o1, Runway, Luma, Minimax — plus Topaz Apollo (interpolation & slow-mo), Chronos, Astra 1 & 2 (generative upscale with creativity, sharpness and realism dials) and Aion.

Audio, music & voice

ElevenLabs, Suno, Udio, MusicGen, OpenAI TTS and Fish Audio — including a built-in Fish voice browser card right on the board.

LLMs, hosted and local

OpenAI's GPT-5 family, Anthropic Claude, Google Gemini, Groq and DeepSeek — plus fully local models through Ollama for zero-cost, private text work.

Generation lanes

Every job gets a lane with elapsed time and live progress. Queue as many as you want, cancel any of them, or flip on auto-generate and let it run.

Sequential prompt queue

Chain prompt cards across the board into an ordered run — promptGOAT walks the queue and fires each prompt in sequence.

Crash-safe recovery

Per-job recovery records are replayed after a crash, and finished outputs are re-scanned from history — a restart never loses a paid generation.

Reference images

Completions can auto-assign themselves as reference images for the next round — iterate image-to-image without leaving the canvas.

Spend caps that actually stop it

Per-job, per-session and per-month limits are checked before a job is sent — and hitting one halts auto-generate cleanly instead of looping on refusals. Leave a batch running overnight and it stops at the number you chose.

Model picker

Local and API models in one searchable picker with favorites — switch a card from a hosted model to a local workflow in two clicks.

Bring your own API keys: every request goes directly from your machine to the provider, at the provider's own price. promptGOAT never proxies, marks up, or meters your generations.
How it works

From key to canvas in minutes.

STEP 01

Bring your keys — or none

The first-run wizard walks you through adding API keys for the services you use. Prefer fully local? It can install ComfyUI and starter models matched to your GPU instead.

STEP 02

Build your board

Drop model cards, prompt cards and references onto the canvas. Wire a composer to your preset library — or install a community pack from the Exchange — and let weighted randomness feed you variations.

STEP 03

Generate, refine, ship

Queue generations across models, edit results in the built-in editor, stitch clips into sequences — and export knowing exactly what the whole thing cost.

Local-first by design

Your keys. Your files.
Your machine.

promptGOAT is a native C++ application, not a web app in a wrapper. There is no promptGOAT cloud between you and your work.

Pricing

Pay once. Own it forever.

No subscription, no tiers, no feature gates. One fee unlocks the entire studio — every backend, the board, the storyboard builder, the vault, the editor, the preset engine — for life.

🐐 Lifetime license

promptGOAT Studio

Limited-time launch price · yours forever · bring your own keys

$20one-time$0 / month, ever
  • The complete studio — every feature, nothing held back
  • All 22 hosted backends + the full local ComfyUI engine
  • Preset Exchange access — browse, publish, vote, get supported
  • All updates included — new workflows & models keep arriving via the catalog
  • 106-structure script builder, infinite board, vault, media editor, preset engine
  • Cost & energy tracking with editable pricing tables
  • Single-seat license · self-service machine moves · 7-day offline grace
  • Instant key delivery by email

Launch pricing — the price will go up. The license never expires, whenever you buy.

Why a one-time fee?

Because promptGOAT doesn't resell compute. You bring your own API keys and pay OpenAI, Google, Kling and the rest directly, at their prices, with zero markup — and local ComfyUI generation costs nothing at all. There's no usage for us to meter, so there's no reason to rent you your own studio.

  1. 1
    Check out with Stripe. Card, Apple Pay or Google Pay on Stripe's secure hosted checkout.
  2. 2
    Your key arrives in seconds. A PGOAT-… license lands in your inbox the moment payment clears.
  3. 3
    Paste it into Settings → License. Activated in one click. Build your first board tonight.

One activation per license, enforced fairly: moving machines is self-service (up to 3 moves per month), and a 7-day offline grace window means travel never locks you out. Requires Windows 10/11 (64-bit); a GPU is only needed for local generation. The $20 launch price is temporary — the license you buy at any price is forever.

Secure checkout by Stripe · Instant key delivery · 14-day money-back guarantee
FAQ

Answers, up front.

For hosted models, yes — you connect your own OpenAI, Google, Kling, ElevenLabs (and other) accounts, and pay those providers directly at their prices. promptGOAT adds zero markup and never proxies your traffic. Prefer not to use any hosted service? Run entirely local through ComfyUI and Ollama — no keys required.
Local generation through ComfyUI works offline once your models are downloaded, and all editing, board and vault features are fully local. Your license checks in periodically and includes a 7-day offline grace window, so a flight or an internet outage never locks you out of your work. Hosted models naturally need a connection.
Each license activates one machine at a time, enforced server-side. Switching PCs is self-service: deactivate on the old machine (or from a machine you no longer have access to) and activate on the new one — up to 3 moves per month, no support ticket needed.
No. ComfyUI is optional — the 22 hosted backends work without it. If you want local generation, the first-run wizard can install ComfyUI and starter models for you, and promptGOAT detects your GPU and VRAM to recommend models that will actually run well on your hardware.
A built-in library of community preset packs — whole categories of prompts you can browse, install, vote on and publish without leaving the app. Packs are words only (never your images or file paths), every download is integrity-checked twice, and every upload is read by a human before it goes live. Authors attach their own donation link — 100% of support goes straight to them; we never touch the money. Your license is your account: no extra sign-up, no passwords.
Only what you send: prompts and reference media go directly to the AI provider you chose for that generation, and your license key checks in with our license server. That's it. Your media library, boards, presets, usage ledger and API keys all stay local — keys are encrypted with Windows DPAPI and scrubbed from logs.
Windows 10 or 11, 64-bit. Any modern CPU handles the studio itself — it's native C++, not Electron. A dedicated NVIDIA GPU is recommended only if you want local ComfyUI generation; hosted models run fine on anything. A macOS build is in development.
Your one-time license includes updates. The app checks automatically and tells you when a new build is available — and new curated workflows and models arrive through the built-in catalog without even needing an update. No upgrade fees, no "pro" re-buy.
If promptGOAT isn't for you, email support@promptgoat.studio within 14 days of purchase for a full refund of your one-time fee. No forms, no hoops.

Stop juggling tabs.
Start directing models.

Your entire AI pipeline — hosted and local — on one canvas, on your machine.
Pay once. Own it forever.

Get promptGOAT

Follow @promptgoat.studio on Instagram →