Nodes/ComfyUI-ThinkingLLM/ThinkingLLM Whisper ASR
ComfyUI Node

ThinkingLLM Whisper ASR

A ComfyUI node in ThinkingLLM/Audio with 9 inputs and 3 outputs.

By goodguy1963·Created 3 months ago·Updated 25 days ago· 13
ThinkingLLM Whisper ASR
  • audio
  • TRANSCRIPT
  • SEGMENTS_JSON
  • RAW_TRACE
model_sizesmall
languageauto
tasktranscribe
devicecpu
compute_typeint8
beam_size5
vad_filtertrue
audio_file_path
CategoryThinkingLLM/Audio

Inputs (9)

NameTypeDefaultDescription
model_sizeCOMBOsmallfaster-whisper model size. small is a reliable Windows-friendly starting point; large-v3 is higher quality but downloads and runs much larger.
languageCOMBOautoAudio language. Use auto to let Whisper detect it.
taskCOMBOtranscribetranscribe preserves the original language; translate returns English.
deviceCOMBOcpucpu is the most reliable Windows default; choose cuda when your faster-whisper/CTranslate2 CUDA runtime is working.
compute_typeCOMBOint8int8 is reliable on CPU. Use float16 or int8_float16 for CUDA.
beam_sizeINT51–10Higher values can improve accuracy but run slower.
vad_filterBOOLEANtrueSkip long silence and non-speech sections before transcription.
audiooptAUDIO
audio_file_pathoptSTRINGOptional local audio file path. M4A, MP3, WAV, FLAC, and other FFmpeg-readable files are decoded to 16 kHz mono WAV before Whisper.

Outputs (3)

NameTypeDescription
TRANSCRIPTSTRING
SEGMENTS_JSONSTRING
RAW_TRACESTRING