ComfyUI Node
VoxCPM Text-to-Speech
A ComfyUI node in DN-VoxCPM with 7 inputs and 1 output.
VoxCPM Text-to-Speech
- model
- audio
◄textVoxCPM is an innovative end-to-end TTS model designed to generate highly realistic speech.►
◄cfg_value2.0►
◄inference_timesteps10►
◄normalizefalse►
◄retry_badcasetrue►
◄max_len4096►
CategoryDN-VoxCPM
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| model | VOXCPM_MODEL | — | |
| text | STRING | VoxCPM is an innovative end-to-end TTS model designed to generate highly realistic speech. | — |
| cfg_value | FLOAT | 2.01–3 | — |
| inference_timesteps | INT | 104–30 | — |
| normalize | BOOLEAN | false | — |
| retry_badcase | BOOLEAN | true | — |
| max_lenopt | INT | 4096100–8192 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |