Model provider · Bring your own keyElevenLabs in a visual AI workflow
Run ElevenLabs' voice models in NodeTool — text-to-speech, voice cloning, dubbing, and sound effects, called with your own ElevenLabs key.
ElevenLabs is the leading voice AI provider: expressive text-to-speech, voice cloning, dubbing across languages, and generative sound effects. In NodeTool, its models are audio nodes you can chain after a script writer or before a video assembler.
ElevenLabs is bring-your-own-key: set `ELEVENLABS_API_KEY` and NodeTool calls ElevenLabs directly at their price.
Calls go straight to ElevenLabs with your key at their list price — NodeTool never proxies or marks up the request.
What ElevenLabs does in NodeTool
Featured ElevenLabs models
NodeTool queries ElevenLabs for the exact models your key can access and exposes each as a node. These are the families you can build with.
Expressive, multilingual TTS with many voices.
Create a custom voice from a short sample.
Generate SFX from a text description.
Frequently asked
- How do I use ElevenLabs in NodeTool?
- Add `ELEVENLABS_API_KEY` in settings, then add an ElevenLabs node and feed it text. The audio comes back onto the canvas for the next step.
- Can I clone a voice in a workflow?
- Yes — ElevenLabs voice models are nodes, so cloning and TTS run inside a pipeline alongside your text and video steps.
- What does ElevenLabs cost in NodeTool?
- ElevenLabs' list price. NodeTool is bring-your-own-key.
Other providers
Run ElevenLabs your way.
Download NodeTool Studio and build across image, video, audio, and text with your own keys.