NodeTool is the open-source creative AI workspace. Every major model from every major provider (FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, and more) runs on one visual canvas using your own keys. Image, video, audio, and text live side by side, with editing tools such as masks, inpaint, outpaint, relight, upscale, layers, and compositing built in. It runs as a desktop app on macOS, Windows, and Linux, or in the browser with NodeTool Cloud.

How is NodeTool different from ComfyUI?

ComfyUI is a specialist image tool built for engineers. NodeTool is a complete creative workspace: image, video, audio, and text on one canvas, with the editing tools creatives actually use. It also covers far more models, across more providers and media types, using your own keys at provider prices.

How is NodeTool different from Figma Weave (formerly Weavy) or other closed SaaS canvases?

Closed tools tie you to a credit system and a hand-picked list of models. NodeTool is open source. You bring your own API keys to every provider, pay those providers directly at their published prices, and own your workflows and files. Cloud is simply our hosting of the same open-source code you can run yourself.

How does pricing work?

NodeTool Studio is free to download and use. NodeTool Cloud is a subscription that covers hosting. In both, you bring your own API keys and pay each provider directly at their list prices. NodeTool does not run models on its own servers, does not issue its own credits, and does not add a markup.

What models does NodeTool support?

The latest 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 machine with MLX, Ollama, llama.cpp, vLLM, and LM Studio.

Independent artists, motion designers, illustrators, and art directors, along with small creative studios, brand teams, and post-production houses that work with AI every day.

Is NodeTool open source?

Yes. Studio and Cloud are built from the same AGPL-3.0 source. Nothing is held back for a paid tier, and you can host it yourself at any time.

All templates

Template·Video

AI Spokesperson

Name: NodeTool
Author: NodeTool

Give a presenter clip a new script. Text-to-speech voices the script, then a lip-sync model redrives the mouth in the source footage so the delivery matches. Useful for localising a take, fixing a fluffed line, or spinning one recording into many variants. Both the speech and lip-sync steps are paid per run.

Download NodeTool How to run it

AI Spokesperson — example output from the NodeTool workflow

The workflow

Workflow EditorAI Spokesperson

Note

Video Input

String Input

Our spring release ships today. Faster renders, sharper output, and a price that did not move.

Text To Speech

Text

Audio

inworld/realtime-tts-1.5-max

Lip Sync

Video

Audio

fal-ai/sync-lipsync/v2/pro

Output

Nodes in this workflow

5 nodes · 5 types

Lip Sync
nodetool.video.LipSync
Output
nodetool.output.Output
String Input
nodetool.input.StringInput
Text To Speech
nodetool.audio.TextToSpeech
Video Input
nodetool.input.VideoInput

How to run it

01
Download NodeTool Studio
Install the free desktop app for macOS, Windows, or Linux. It runs on your own machine, no account required to start.
02
Open the AI Spokesperson template
Browse the built-in template library inside Studio and open this workflow onto the canvas. Every node is already wired up.
03
Add your keys
Connect the providers this workflow uses (Lip Sync, Text To Speech, Video Input). Bring your own keys — you pay the provider directly.
04
Run and remix
Hit Run to execute the graph and watch results stream in. Swap models, edit prompts, or rewire nodes to make it yours.