ComfyUI Node
Qwen3-TTS Synthesis
A ComfyUI node in AIIA/Synthesis with 18 inputs and 1 output.
Qwen3-TTS Synthesis
- qwen_model
- reference_audio
- audio
◄text你好，这是 Qwen3-TTS 的测试。►
◄languageChinese►
◄speakerVivian►
◄voice_presetNone►
◄instruct►
◄reference_text►
◄zero_shot_modefalse►
◄emotionNone►
◄dialectNone►
◄seed42►
◄speed1.00►
◄cfg_scale1.5►
◄temperature0.8►
◄top_k20►
◄top_p0.95►
◄max_batch_char1000►
CategoryAIIA/Synthesis
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| qwen_model | QWEN_MODEL | — | |
| text | STRING | 你好，这是 Qwen3-TTS 的测试。 | — |
| language | COMBO | Chinese | 11 options: Auto, Chinese, English, Japanese, Korean, German, +5 |
| speakeropt | COMBO | Vivian | 9 options: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, +3 |
| voice_presetopt | COMBO | None | Built-in voice preset for Base/Clone models. Used when no reference_audio is connected. Auto-enables zero-shot mode. |
| instructopt | STRING | — | |
| reference_audioopt | AUDIO | — | |
| reference_textopt | STRING | — | |
| zero_shot_modeopt | BOOLEAN | false | — |
| emotionopt | COMBO | None | 20 options: None, Happy (开心), Sad (悲伤), Angry (愤怒), Excited (兴奋), Gentle (温柔), +14 |
| dialectopt | COMBO | None | 19 options: None, Mandarin (普通话), Cantonese (粤语), Shanghainese (上海话), Sichuanese (四川话), Northeastern (东北话), +13 |
| seedopt | INT | 42-1–2147483647 | — |
| speedopt | FLOAT | 1.000.5–2 | — |
| cfg_scaleopt | FLOAT | 1.51–10 | — |
| temperatureopt | FLOAT | 0.80.1–2 | — |
| top_kopt | INT | 200–100 | — |
| top_popt | FLOAT | 0.950–1 | — |
| max_batch_charopt | INT | 1000100–32768 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |