Nodes/ComfyUI_Eclipse/Transcribe Audio
ComfyUI Node

Transcribe Audio

Recognize speech or sung words with the local Whisper large-v3 model. Outputs text and full-audio timing for review, subtitles or lyric captions. No supplied lyrics are required.

By r-vage·Created 11 months ago·Updated about 9 hours ago· 36
Transcribe Audio
  • audio
  • vocals
  • transcript
  • timing_json
  • srt
  • report
◄languageAuto►
◄deviceauto►
Category🌒 Eclipse/ Audio

Inputs (4)

NameTypeDefaultDescription
audioAUDIOComplete recording. Output timestamps start at this audio's time zero.
languageCOMBOAuto101 options: Auto, en, zh, de, es, ru, +95
deviceCOMBOauto3 options: auto, cpu, cuda
vocalsoptAUDIOOptional isolated vocals with the same time zero and duration as audio (within 50 ms).

Outputs (4)

NameTypeDescription
transcriptSTRING—
timing_jsonSTRING—
srtSTRING—
reportSTRING—