ComfyUI Node: MMS Audio-Text Aligner (SRT)

Authored by hnvcam

Created

Updated

0 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

audio/alignment

Inputs

audio AUDIO
text STRING
language
  • auto
  • English
  • Vietnamese
  • Chinese (Mandarin)
  • Spanish
  • French
  • German
  • Italian
  • Portuguese
  • Russian
  • Japanese
  • Korean
  • Arabic
  • Hindi
  • Bengali
  • Indonesian
  • Malay
  • Thai
  • Turkish
  • Polish
  • Dutch
  • Swedish
  • Finnish
  • Greek
  • Czech
  • Ukrainian
  • Hebrew
  • Persian
  • Urdu
  • Tamil
  • Telugu
  • Filipino (Tagalog)
  • custom
custom_language_code STRING
romanize BOOLEAN
segmentation_mode
  • single_word
  • max_chars
  • punctuation
  • newlines
  • max_chars+punctuation
  • max_chars+punctuation+newlines
max_chars_per_line INT
remove_punctuation BOOLEAN
output_name STRING
gap_ms INT
split_count INT
precision
  • bf16
  • fp16
  • fp8
  • fp32
chunk_with_whisper BOOLEAN
whisper_model_size
  • tiny
  • base
  • small
  • medium
  • large-v3
chunk_max_seconds INT

Outputs

STRING

STRING

Extension: ComfyUI-MMS-Aligner

ComfyUI custom node that force-aligns audio with text into an SRT file using Meta's MMS models.

Authored by hnvcam

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more