ComfyUI Node
Raon OpenTTS Generate (Voice Clone)
Zero-shot voice cloning with Raon-OpenTTS (F5-TTS-style CFM/DiT + HiFi-GAN).
Raon OpenTTS Generate (Voice Clone)
- raon_model
- ref_audio
- audio
◄textHello! This is Raon OpenTTS running natively inside ComfyUI.►
◄ref_text►
◄steps32►
◄cfg_strength2.00►
◄sway_sampling_coef-1.00►
◄speed1.00►
◄seed42►
◄fix_duration_seconds0.0►
◄target_rms0.10►
◄use_vad_durationtrue►
◄cross_fade_ms150►
◄do_splittrue►
◄max_chars0►
CategoryRaonOpenTTS
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| raon_model | RAON_OPENTTS_MODEL | — | |
| text | STRING | Hello! This is Raon OpenTTS running natively inside ComfyUI. | Text to synthesize. Long text is split into chunks automatically and cross-faded together. |
| ref_audio | AUDIO | Reference voice clip for zero-shot cloning. Clean speech with little noise works best. | |
| ref_text | STRING | Exact transcript of the reference clip. Strongly improves cloning quality. Use the Whisper Transcribe node to generate it. | |
| steps | INT | 321–64 | NFE steps for the flow-matching ODE (euler + EPSS schedule). 32 is the official default. |
| cfg_strength | FLOAT | 2.000–10 | Classifier-free guidance strength. 2.0 is the official default; 0 disables CFG. |
| sway_sampling_coef | FLOAT | -1.00-2–2 | Sway sampling coefficient for the time schedule. -1.0 is the official default. |
| speed | FLOAT | 1.000.5–2 | Speech-rate multiplier for duration estimation (>1 = faster). |
| seed | INT | 420–2147483647 | 0 uses the current random state. A positive value is repeatable (incremented per text chunk). |
| fix_duration_seconds | FLOAT | 0.00–60 | Force the generated segment length in seconds. 0 estimates it from the reference speech rate (official behaviour). |
| target_rms | FLOAT | 0.100–0.5 | Loudness normalization target for the reference clip (official: 0.1). |
| use_vad_duration | BOOLEAN | true | Estimate the generation length from the VAD-trimmed reference length (official default, robust for quiet speakers) while conditioning on the untrimmed audio. |
| cross_fade_ms | FLOAT | 1500–500 | Cross-fade between generated text chunks in milliseconds (official: 150). |
| do_split | BOOLEAN | true | Split long text into chunks and generate them one by one (cross-faded together). Off = always one chunk, whatever the length. |
| max_chars | INT | 00–2000 | Chunk size budget in UTF-8 bytes. 0 = auto, estimated from the reference speech rate (official behaviour: ref_bytes/ref_seconds x (22 - ref_seconds)). Any positive value forces that budget, so the split becomes deterministic across speakers. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |