ComfyUI Node
FireRedTTS3 Voice Clone
Zero-shot voice cloning with FireRedTTS3 base or instruct.
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)
| Name | Type | Default | Description |
|---|---|---|---|
| firered_model | FIREREDTTS3_MODEL | — | |
| text | STRING | Hello! This is FireRedTTS3 running natively inside ComfyUI. | Text to synthesize. Long text is split into sentences automatically when do_split is on. |
| prompt_audio | AUDIO | Reference voice clip for zero-shot cloning. Clean speech with little noise works best. | |
| prompt_text | STRING | Exact transcript of the reference clip. Strongly improves cloning quality. | |
| language | COMBO | auto | Language or Chinese dialect tag. auto uses FastText (24 languages) with zh/ja/en heuristic fallback. For best cloning, match the prompt audio language. |
| n_timesteps | INT | 101–50 | Flow-matching steps per generated audio patch. 10 is the official default; more is slower with diminishing returns. |
| inference_cfg | FLOAT | 2.000–4 | Classifier-free guidance strength for the flow head. 0 disables CFG. Official defaults: 2.0 for cloning, 1.2 for design/edits. |
| stop_threshold | FLOAT | 0.500.05–0.95 | Stop-token probability threshold that ends generation. Higher values allow longer audio. |
| seed | INT | 420–2147483647 | 0 uses the current random state. A positive value is repeatable. |
| max_audio_seconds | FLOAT | 644–160 | Hard cap on generated audio length per sentence (64s is the official maximum). |
| do_tn | BOOLEAN | true | Run text normalization (numbers, dates, units to spoken form). Chinese/English use local wetext; other languages get basic cleaning. |
| do_split | BOOLEAN | true | Split long text into sentences and generate them one by one (cross-faded together). |
| cross_fade_ms | FLOAT | 500–500 | Cross-fade between sentence segments in milliseconds. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |