ComfyUI Node: Audio To Text (mtb)

Authored by melMass

Created

Updated

720 stars

Run Audio To Text (mtb) 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

mtb/audio

Inputs

pipeline WHISPER_PIPELINE
audio AUDIO
language
  • auto
  • de
  • en
  • es
  • fr
  • it
  • ja
  • ko
  • nl
  • pt
  • ru
  • zh
return_timestamps BOOLEAN

Outputs

STRING

WHISPER_OUTPUT

Extension: MTB Nodes

NODES: Face Swap, Film Interpolation, Latent Lerp, Int To Number, Bounding Box, Crop, Uncrop, ImageBlur, Denoise, ImageCompare, RGV to HSV, HSV to RGB, Color Correct, Modulo, Deglaze Image, Smart Step, ...

Authored by melMass

Looking for a different node?

Run Audio To Text (mtb) 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.

Learn more