Nodes/FireRedTTS3-ComfyUI/FireRedTTS3 Voice Clone
ComfyUI Node

FireRedTTS3 Voice Clone

Zero-shot voice cloning with FireRedTTS3 base or instruct.

By Saganaki22·Created 11 days ago·Updated 7 days ago· 17
FireRedTTS3 Voice Clone
  • firered_model
  • prompt_audio
  • audio
textHello! This is FireRedTTS3 running natively inside ComfyUI.
prompt_text
languageauto
n_timesteps10
inference_cfg2.00
stop_threshold0.50
seed42
max_audio_seconds64
do_tntrue
do_splittrue
cross_fade_ms50
CategoryFireRedTTS3

Inputs (13)

NameTypeDefaultDescription
firered_modelFIREREDTTS3_MODEL
textSTRINGHello! This is FireRedTTS3 running natively inside ComfyUI.Text to synthesize. Long text is split into sentences automatically when do_split is on.
prompt_audioAUDIOReference voice clip for zero-shot cloning. Clean speech with little noise works best.
prompt_textSTRINGExact transcript of the reference clip. Strongly improves cloning quality.
languageCOMBOautoLanguage or Chinese dialect tag. auto uses FastText (24 languages) with zh/ja/en heuristic fallback. For best cloning, match the prompt audio language.
n_timestepsINT101–50Flow-matching steps per generated audio patch. 10 is the official default; more is slower with diminishing returns.
inference_cfgFLOAT2.000–4Classifier-free guidance strength for the flow head. 0 disables CFG. Official defaults: 2.0 for cloning, 1.2 for design/edits.
stop_thresholdFLOAT0.500.05–0.95Stop-token probability threshold that ends generation. Higher values allow longer audio.
seedINT420–21474836470 uses the current random state. A positive value is repeatable.
max_audio_secondsFLOAT644–160Hard cap on generated audio length per sentence (64s is the official maximum).
do_tnBOOLEANtrueRun text normalization (numbers, dates, units to spoken form). Chinese/English use local wetext; other languages get basic cleaning.
do_splitBOOLEANtrueSplit long text into sentences and generate them one by one (cross-faded together).
cross_fade_msFLOAT500–500Cross-fade between sentence segments in milliseconds.

Outputs (1)

NameTypeDescription
audioAUDIO