ComfyUI Node: ElevenLabs Speech to Text
Run ElevenLabs Speech to Text without installing ComfyUI
This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.
Category
partner/audio/ElevenLabs
Inputs
audio AUDIO
model COMFY_DYNAMICCOMBO_V3
language_code STRING
num_speakers INT
seed INT
Outputs
STRING
STRING
STRING
Extension: ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Authored by Comfy-Org
Looking for a different node?
More nodes in ComfyUI
Run ElevenLabs Speech to Text without installing ComfyUI
This node already runs on ComfyICU. Open it in the browser, hit run, and you're billed for GPU seconds — not for setup, and not while you're idle.