ComfyUI Node
VoxCPM SRT Processor (from Scratch)
A ComfyUI node in audio/tts with 13 inputs and 1 output.
VoxCPM SRT Processor (from Scratch)
- model
- cache_group
- AUDIO
◄srt_text1
00:00:00,500 --> 00:00:02,000
speaker1 Hello world.
►
◄normalize_texttrue►
◄stretch_methodlibrosa►
◄stretch_n_fft320►
◄stretch_hop_length8►
◄keep_model_loadedtrue►
◄cfg_value2.0►
◄inference_timesteps30►
◄seed-1►
◄retry_max_attempts3►
◄retry_threshold6.00►
Categoryaudio/tts
Inputs (13)
| Name | Type | Default | Description |
|---|---|---|---|
| model | VOXCPM_MODEL | — | |
| cache_group | CACHE_GROUP | — | |
| srt_text | STRING | 1 00:00:00,500 --> 00:00:02,000 speaker1 Hello world. | — |
| normalize_text | BOOLEAN | true | — |
| stretch_method | COMBO | librosa | 3 options: none, librosa, pydub |
| stretch_n_fft | INT | 320128–8192 | — |
| stretch_hop_length | INT | 88–2048 | — |
| keep_model_loaded | BOOLEAN | true | — |
| cfg_value | FLOAT | 2.01–10 | — |
| inference_timesteps | INT | 301–100 | — |
| seed | INT | -1-1–9223372036854776000 | — |
| retry_max_attempts | INT | 30–10 | — |
| retry_threshold | FLOAT | 6.002–20 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| AUDIO | AUDIO | — |