ComfyUI Node
VoxCPM SRT Auto-Dubber (Line-by-Line Ref)
A ComfyUI node in audio/tts with 14 inputs and 1 output.
VoxCPM SRT Auto-Dubber (Line-by-Line Ref)
- model
- original_audio
- AUDIO
◄source_srt_textSource Language SRT (Transcript)...►
◄target_srt_textTarget Language SRT (Translation)...►
◄normalize_texttrue►
◄stretch_methodlibrosa►
◄keep_model_loadedtrue►
◄stretch_n_fft320►
◄stretch_hop_length8►
◄cfg_value2.0►
◄inference_timesteps30►
◄seed-1►
◄retry_max_attempts3►
◄retry_threshold6.00►
Categoryaudio/tts
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| model | VOXCPM_MODEL | — | |
| original_audio | AUDIO | — | |
| source_srt_text | STRING | Source Language SRT (Transcript)... | — |
| target_srt_text | STRING | Target Language SRT (Translation)... | — |
| normalize_text | BOOLEAN | true | — |
| stretch_method | COMBO | librosa | 3 options: none, librosa, pydub |
| keep_model_loaded | BOOLEAN | true | — |
| stretch_n_fft | INT | 320128–8192 | — |
| stretch_hop_length | INT | 88–2048 | — |
| 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 | — |