UGC product video
Turns out I needed the green one.
A self-aware purchase becomes a small source of reassurance as the same cup follows one chaotic day.
Explore projectNodeTool Cloud is in alpha โ run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it โ
Create images, video, audio, and text with agents that work alongside you. Describe what you want, let the agent build it, then take over whenever you like.
Free and open source, AGPL-3.0. macOS, Windows, and Linux.

Give the agent a brief. It drafts the script, boards the shots, renders the takes, and cuts them on a timeline. What comes back is a project you can open. Change any part of it yourself, or send the agent back in with a note about the one shot you want different.

Tell the agent your concept, style, and tone. It drafts the script, casts the voices, and sets the visual direction.
The agent boards the scenes, generates the footage, syncs the audio, and cuts it on a multi-track timeline. Every step lands in a project you can open, on your keys, at provider prices.

Jump in at any moment. Swap a voice take, re-roll a clip, trim frames. Or hand the project back to the agent with one note and keep going.

Everything the agent made stays open. Re-roll a shot, audition another take, retime the cut, change a line, swap a reference, or adjust the workflow behind it. Storyboard, script, timeline, sketch, and 3D scene all sit on the canvas you generate on, and the agent works every one of them through the same tools you click.

Board the film shot by shot. Generate cheap stills to lock the look, then animate only the shots you approved.

Draft the dialogue, cast a voice per character, and audition alternate readings. Change the words and the take flags itself stale, so you see what still needs voicing.

Arrange, trim, and layer generated video and audio across tracks, down to the frame and the stem. The agent edits the same document when you ask it to tighten the opening.

Sketch, paint, and blend hand-drawn elements with generated layers. Bind a layer to a prompt and regenerate that layer alone.

Place primitives and lights in a glTF scene by hand or by tool call. The same operations run headlessly, so a scene is reproducible.
Ads, catalogue images, dubbed videos, and storyboards. Start with an example.
UGC product video
A self-aware purchase becomes a small source of reassurance as the same cup follows one chaotic day.
Explore project
Directed campaign kit
One clean cup reference becomes a kinetic launch world, two social formats, and a bounded revision.
Explore project
Product commercials
Fresh coffee pours, she takes a quiet moment, then heads out with her cup. Three shots follow one morning ritual.
Explore project
Impossible product worlds
A desert flight reveals a pool in a giant cup. A woman jumps in, then drinks from the same product at human scale.
Explore project
Product catalogue assets
Turn one product photo into a cutout, studio shots, and seasonal scenes.
Explore project
Multilingual video
An English presenter, revoiced in Spanish. Edit the translation and revise individual voice lines.
Explore project
Storyboard to trailer
The Next Tide: a six-shot storyboard with a shared cast, locations, and props.
Explore projectRoute your shots through the best video, image, audio, and language models, or run open weights on your own hardware. Switch in one click. Pay each provider directly, at their published price.
One job, one tool, one screen. Each app is a shipped workflow with a form on top, so an operator runs it without opening the canvas.

Settle the message. Direct the campaign image.

One brand identity drives two deliverables.

Generate a gallery, pick one, polish it.

Drag five sliders and watch the photo re-render โ then run the same grade over a whole folder.

Relight the product. Change the set. Keep the product fixed.
Turn a product photo into a controlled moving shot.

Approve the frame, then animate the shot.

Build a testimonial, then finish it for social.

Change one thing about a photo and keep the rest.
Bring your own keys and switch providers in one click. You own the project file, the workflow, and the final cut.
Connect to OpenAI, Anthropic, Gemini, FAL, KIE, Replicate, and the video specialists. Keys stay on your disk in Studio, encrypted in Cloud.
If an image costs $0.03 at the provider, you pay $0.03 to the provider. No credit packs. NodeTool takes no cut.
Studio and Cloud are built from the same AGPL-3.0 source, with no paywalled features. Read it, fork it, or host it yourself.
The board, the script with its takes, and the multi-track cut are ordinary files on your disk. Export a .nodetool bundle and open it anywhere.
What that costs a month, model by model, is on the pricing page.
When a project comes out right, keep the process that made it. Chain models, editors, and code into a node graph you can re-run on new inputs, ship as an app, or drive headless from the CLI.
A hosted platform makes the film and keeps the model list, the billing, and the project. Here is the same table with the studio open.
| ย | NodeTool | Hosted platforms |
|---|---|---|
| Models | Every major provider, switched in one click | The list they picked |
| When a better model ships | Add it the day it ships | Wait for them to add it |
| What you pay | Provider list prices, on your own keys | Their credits |
| What you keep | The board, the takes, and the multi-track cut as an editable project | An exported video. The project stays in their app. |
| Source | Open, AGPL-3.0 | Closed |
| Where it runs | Desktop app and browser, self-host any time | Their servers only |
Comparing against a specific product? See NodeTool and ComfyUI and NodeTool and Figma Weave.
Take Seedance, one of today's best video models. FAL, Replicate, and KIE each sell it at a different price, and NodeTool lets you pick the cheapest. When the next Veo or Kling arrives, you switch in one click.
That is what holding the keys buys you: the best model at the best price each week, and nothing to lose if a tool gets bought, repriced, or shut down.
Two editions, one recommendation
Studio is the desktop edition and the production path. Cloud is the browser edition for evaluation and lightweight access while it is in alpha.
Desktop edition
Browser edition ยท Alpha preview
Studio is the production path. Cloud is the browser preview for evaluation while it is in alpha.
Runs on your computer. Local projects and supported local models can remain available without a network connection.
Go to StudioRuns in your browser with nothing to install. Use it for evaluation and lightweight access while it is in alpha.
Go to Cloud (alpha)Bring your own code onto the canvas through the SDK, the CLI, or an MCP server.
Go to DevelopersTurn a brief into a production workflow you run again for every product, market, and variant.
Go to MarketingNodeTool is an open-source agent-first creative workspace. Create and edit images, video, audio, and text with agents that work alongside you. Describe what you want, let the agent build it, then take over whenever you like. You get an editable project, not just a finished file: your workflows, assets, and edits stay together. Use supported local models or connect cloud providers with your own keys.
Read more โYes. The whole project is AGPL-3.0 on GitHub. Studio and Cloud are built from the same source, and nothing is held back for a paid tier. You can host it yourself at any time.
Read more โNodeTool Studio, the desktop app, is free and open source. Cloud pricing and access can change during alpha, so check the Cloud page before use. In both editions, provider charges are separate: you connect your own provider account and pay that provider directly. Supported local models in Studio have no provider charge per call, but they use your hardware and electricity.
Read more โNodeTool Studio stores the workspace, workflows, files, and configured credentials on your machine. Supported open-weight models can run locally through MLX, Ollama, llama.cpp, vLLM, and LM Studio. When you call a hosted model, the request leaves your machine for that provider. Cloud uses hosted project storage; review the current privacy policy and terms before using sensitive material.
Read more โThe leading models, including Flux, Seedance, Wan, Veo, Kling, Hailuo, Qwen Image, Whisper, ElevenLabs, and Suno, reached through providers such as FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, Together, Groq, Mistral, OpenRouter, and HuggingFace. Models can also run on your own computer through MLX, Ollama, llama.cpp, vLLM, and LM Studio.
Read more โThe node canvas, sketch pad, storyboard, video timeline, script editor, 3D scene, and app builder expose operations that agents can call as tools. The agent can change the workflow or project on the same surfaces you use, and the execution record shows tool calls, results, errors, and interventions. The toolbelt is also exposed over MCP for compatible external agents.
Read more โNo. Studio can use hosted providers, where the model runs on the provider's hardware. A GPU matters only when you choose to run supported open-weight models on your computer. The requirement then depends on the model and runtime; smaller models may run on CPU at lower speed.
Read more โNodeTool is open source under AGPL-3.0. Star it on GitHub, join us on Discord, and share workflows with the artists and studios already using it on real jobs.
Questions, bug reports, feature requests โ we answer.
Download the open-source studio for macOS, Windows, and Linux. Free, AGPL-3.0. Or try Cloud in your browser, in alpha, with nothing to install.