Nodes/VRGameDevGirl Video Enhancement Nodes/VRGDG VoxCPM2 Voice Clone / TTS
ComfyUI Node

VRGDG VoxCPM2 Voice Clone / TTS

A ComfyUI node in VRGDG/Audio with 18 inputs and 4 outputs.

By vrgamegirl19·Created about a year ago·Updated 22 days ago· 533
VRGDG VoxCPM2 Voice Clone / TTS
  • reference_audio
  • prompt_audio
  • audio
  • saved_audio_path
  • sample_rate
  • status
textHello from VoxCPM2.
modetext_to_speech
deviceauto
cfg_value2.0
inference_timesteps10
load_denoiserfalse
normalize_textfalse
retry_badcasetrue
retry_badcase_max_times3
retry_badcase_ratio_threshold6.0
min_len2
max_len4096
save_filename_prefixvoxcpm2
reference_audio_path
prompt_audio_path
prompt_text
CategoryVRGDG/Audio

Inputs (18)

NameTypeDefaultDescription
textSTRINGHello from VoxCPM2.What you want the model to say. For cloning modes, this is the new target speech, not the transcript of your reference clip.
modeCOMBOtext_to_speechChoose how VoxCPM2 should speak: - text_to_speech: regular TTS with no voice reference. - voice_design: zero-shot styled speech guided by your wording alone. - prompt_continuation: continue from a prompt clip using prompt_audio plus prompt_text. - controllable_clone: easiest voice clone. Provide a clean reference clip. - ultimate_clone: strongest cloning mode. Provide a reference clip and the exact transcript in prompt_text.
deviceCOMBOautoauto picks CUDA when available and falls back to CPU. CUDA is strongly recommended for VoxCPM2.
cfg_valueFLOAT2.00–20Classifier-free guidance strength. A good starting point is 2.0. Lower can sound looser; higher can sound more forced.
inference_timestepsINT101–200Number of inference steps. 10 is a solid default. Higher may improve quality slightly but is slower.
load_denoiserBOOLEANfalseOptional cleanup for noisy prompt or reference audio before cloning. Useful if your source clip has hiss, room noise, or light background noise.
normalize_textBOOLEANfalseNormalize text before generation. Can help with number/date expansion and cleaner pronunciation on some inputs.
retry_badcaseBOOLEANtrueRetry obviously bad generations automatically. This can improve reliability but may take longer.
retry_badcase_max_timesINT31–10Maximum retry attempts when retry_badcase is enabled.
retry_badcase_ratio_thresholdFLOAT6.01–20Bad-case threshold for retry logic. Leave this alone unless you are tuning generation behavior.
min_lenINT21–128Minimum generated audio token length. Usually safe to leave at the default.
max_lenINT409632–16384Maximum generated token length. Increase if long text is getting cut off. Higher values can use more VRAM and time.
save_filename_prefixSTRINGvoxcpm2Base name for the saved WAV file in ComfyUI/output/VRGDG_AudioFiles.
reference_audiooptAUDIOSpeaker reference for voice cloning. Use a clean single-speaker clip, ideally 10 to 30 seconds.
reference_audio_pathoptSTRINGSpeaker reference for voice cloning. Use a clean single-speaker clip, ideally 10 to 30 seconds.
prompt_audiooptAUDIOPrompt/continuation audio. Use this for prompt_continuation, or for ultimate_clone when you want the model to match a specific spoken example.
prompt_audio_pathoptSTRINGPrompt/continuation audio. Use this for prompt_continuation, or for ultimate_clone when you want the model to match a specific spoken example.
prompt_textoptSTRINGExact transcript of the prompt/reference clip. Required for prompt_continuation and ultimate_clone. Match the spoken words as closely as possible.

Outputs (4)

NameTypeDescription
audioAUDIO
saved_audio_pathSTRING
sample_rateINT
statusSTRING