ComfyUI Node: VibeVoice TTS
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
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more