ComfyUI Node
VibeVoice Voice Design
A ComfyUI node in Ninode Utils/Voice Design with 13 inputs and 2 outputs.
VibeVoice Voice Design
- reference_audio
- voice_id
- trial_audio
◄promptA narrator telling a suspenseful story, with a deep and magnetic voice, varying speech pace to create a tense and mysterious atmosphere.►
◄preview_textIt was late at night, and he was alone in the old house. Faint footsteps could be heard outside the window. He held his breath and slowly, slowly, walked toward the creaking door...►
◄model_name▾►
◄attention_modesdpa►
◄cfg_scale1.30►
◄inference_steps10►
◄seed42►
◄custom_voice_id►
◄quantize_llm_4bitfalse►
◄temperature0.95►
◄top_p0.95►
◄force_offloadfalse►
CategoryNinode Utils/Voice Design
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | A narrator telling a suspenseful story, with a deep and magnetic voice, varying speech pace to create a tense and mysterious atmosphere. | — |
| preview_text | STRING | It was late at night, and he was alone in the old house. Faint footsteps could be heard outside the window. He held his breath and slowly, slowly, walked toward the creaking door... | — |
| model_name | COMBO | Select the VibeVoice model to use. Official models will be downloaded automatically. | |
| attention_mode | COMBO | sdpa | Attention implementation: Eager (safest), SDPA (balanced), Flash Attention 2 (fastest) |
| cfg_scale | FLOAT | 1.300.1–50 | Classifier-Free Guidance scale. Higher values increase adherence to the voice prompt. |
| inference_steps | INT | 101–500 | Number of diffusion steps for audio generation. |
| seed | INT | 420–18446744073709550000 | Seed for reproducibility. Set to 0 for a random seed on each run. |
| custom_voice_idopt | STRING | — | |
| reference_audioopt | AUDIO | Reference audio for voice cloning (optional). If provided, will be used as speaker voice. | |
| quantize_llm_4bitopt | BOOLEAN | false | Quantize the Qwen2.5 LLM to 4-bit NF4 via bitsandbytes. |
| temperatureopt | FLOAT | 0.950–2 | Controls randomness in generation. |
| top_popt | FLOAT | 0.950–1 | Nucleus sampling (Top-P). |
| force_offloadopt | BOOLEAN | false | Force model to be offloaded from VRAM after generation. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| voice_id | STRING | — |
| trial_audio | STRING | — |