ComfyUI-TranscriptionTools
Transcribe audio and video files in ComfyUI.
Nodes (8)
Save the WAV bytes this pack passes around as an actual file
Bridge VideoHelperSuite audio into this pack
The plain audio-file entry point into this pack's Whisper nodes
Transcribe a whole folder of files in one pass
Pull the soundtrack out of a video file for Whisper
Pick your Whisper size and language
Turn audio into text, one file at a time
Transcribe a whole folder, saved straight to disk
ComfyUI Transcription Tools
This package provides custom nodes for ComfyUI to perform transcription tasks on audio and video file inputs. Well suited for long duration inputs. Includes multi-language support and batch processing of many files at once.
<img src="assets/workflow_example.jpg" alt="isolated" width="800"/>Note: To text (Debug) is part of Derfuu_ModdedNodes.
Documentation
Supported Transcription Models
Special Thanks
The team supporting ComfyUI-VideoHelperSuite which provided insrumental examples in the development of this tool.