ComfyUI Node: VibeVoice TTS

Authored by wildminder

Created

Updated

589 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/tts

Inputs

model_name
  • VibeVoice-1.5B
  • VibeVoice-Large
text STRING
quantize_llm_4bit BOOLEAN
attention_mode
  • eager
  • sdpa
  • flash_attention_2
  • sage
cfg_scale FLOAT
inference_steps INT
seed INT
do_sample BOOLEAN
temperature FLOAT
top_p FLOAT
top_k INT
force_offload BOOLEAN
speaker_1_voice AUDIO
speaker_2_voice AUDIO
speaker_3_voice AUDIO
speaker_4_voice AUDIO

Outputs

AUDIO

Extension: ComfyUI-VibeVoice

VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio

Authored by wildminder

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