ComfyUI Whisper

Transcribe audio and add subtitles to videos using Whisper in ComfyUI. Support multiple languages, prompt guidance and multiple whisper models.

Last tested: 2 January 2026 (ComfyUI v0.7.0@f2fda02 | Torch 2.9.1 | Triton 3.5.1 | Python 3.10.12 | RTX4090 | CUDA 13.0 | Debian 12)

⭐ Support

If you like my projects and wish to see updates and new features, please consider supporting me. It helps a lot!

Installation

Install via ComfyUI Manager

Usage

Load this workflow into ComfyUI

Models are auto-downloaded to /ComfyUI/models/stt/whisper

Supported Models

'tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'large-v3-turbo', 'turbo'

Nodes

Apply Whisper

Transcribe audio and get timestamps for each segment and word.

Add Subtitles To Frames

Add subtitles on the video frames. You can specify font family, font color and x/y positions.

Add Subtitles To Background (Experimental)

Add subtitles like wordcloud on blank frames

Save SRT

Export alignments as SRT files in /ComfyUI/output/srt directory

Updates

2 January 2026

• Export alignments as SRT
• Add torchcodec to requirements

27 August 2025

• Merge #22 by @francislabountyjr for model patcher, more whisper models support, comfyui model directory support
• Merge #18 by @qy8502 for Prompt Guidance support
• Support YRDZST Semibold Font

2 May 2025

• Merge #15 by @niknah for language selection

Credits

• comfyanonymous/ComfyUI

• Kosinkadink/ComfyUI-VideoHelperSuite

• melMass/comfy_mtb

License

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)