ComfyUI Node
OmniVoice TTS
A ComfyUI node in audio/tts/OmniVoice with 15 inputs and 1 output.
OmniVoice TTS
- model
- ref_audio
- audio
◄textHello from OmniVoice.►
◄languageEnglish►
◄instruct►
◄speed1.00►
◄duration0.0►
◄num_step28►
◄cfg3.0►
◄seed0►
◄t_shift1.00►
◄denoisefalse►
◄preprocess_prompttrue►
◄postprocess_outputtrue►
◄ref_text►
Categoryaudio/tts/OmniVoice
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| model | OMNIVOICE_MODEL | — | |
| text | STRING | Hello from OmniVoice. | The actual words OmniVoice should generate as speech. For voice cloning, put the target sentence here and put the transcript of the reference clip into ref_text. |
| language | STRING | English | Language name for the generated speech, for example English or Chinese. Leave at English unless you are intentionally switching languages. |
| instruct | STRING | Optional speaking style or character direction. This affects delivery and tone, not the literal transcript. | |
| speed | FLOAT | 1.000.25–4 | Playback/speaking speed target. 1.0 is normal, lower is slower, higher is faster. |
| duration | FLOAT | 0.00–300 | Optional target duration in seconds. Set to 0 to let OmniVoice estimate duration automatically from the text. |
| num_step | INT | 281–128 | Iterative generation steps. The node default is 28 as the current quality baseline; higher values are slower and may or may not help further depending on the prompt. |
| cfg | FLOAT | 3.00–20 | Classifier-Free Guidance scale. The node default is 3.0 for the current tuned baseline; this pushes the result to follow the conditioning more strongly and can change timbre and articulation noticeably. |
| seed | INT | 00–9223372036854776000 | Random seed for OmniVoice generation. With the current deterministic defaults this mainly matters if stochastic settings are re-enabled later, but it is exposed for reproducibility and future tuning. |
| t_shift | FLOAT | 1.000–2 | Mask-schedule shift used by OmniVoice's iterative decoding. The node default is 1.0 as the current tuned baseline for this custom node. |
| denoise | BOOLEAN | false | Adds OmniVoice's denoise control token during generation. The node default is disabled because that is currently giving better audio on this setup. |
| preprocess_prompt | BOOLEAN | true | Preprocess the reference prompt before tokenization. This can trim long reference audio, remove silences, and normalize the prompt path for voice cloning. |
| postprocess_output | BOOLEAN | true | Postprocess the generated audio after decoding. This can remove long silences, normalize level behavior, and add fade/padding to avoid abrupt starts or ends. |
| ref_audioopt | AUDIO | — | |
| ref_textopt | STRING | Required only for voice cloning. Enter the transcript of ref_audio, not the target text to generate. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |