ComfyUI Node
Qwen TTS Multi Speaker Node
A ComfyUI node in Vantage/Audio/Qwen3 TTS with 23 inputs and 1 output.
Qwen TTS Multi Speaker Node
- speaker_prompts
- model
- background_music
- AUDIO
◄dialogue_text—►
◄deviceinherit►
◄attentioninherit►
◄languageAuto►
◄music_volume0.40►
◄music_looptrue►
◄music_trimtrue►
◄music_fade_in_ms500►
◄music_fade_out_ms500►
◄duckingfalse►
◄ducking_strength0.25►
◄ducking_fade_ms200►
◄seed0►
◄max_new_tokens_per_line2048►
◄top_p0.80►
◄top_k20►
◄temperature1.00►
◄repetition_penalty1.05►
◄soft_limiterfalse►
◄unload_model_after_generatefalse►
CategoryVantage/Audio/Qwen3 TTS
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| dialogue_text | STRING | — | |
| speaker_prompts | DICT | — | |
| model | QWEN_TTS_MODEL | — | |
| device | COMBO | inherit | 5 options: inherit, auto, cuda, mps, cpu |
| attention | COMBO | inherit | 6 options: inherit, auto, sage_attn, flash_attn, sdpa, eager |
| language | COMBO | Auto | 11 options: Auto, Chinese, English, Japanese, Korean, French, +5 |
| background_musicopt | AUDIO | — | |
| music_volumeopt | FLOAT | 0.400–2 | — |
| music_loopopt | BOOLEAN | true | — |
| music_trimopt | BOOLEAN | true | — |
| music_fade_in_msopt | INT | 5000–10000 | — |
| music_fade_out_msopt | INT | 5000–10000 | — |
| duckingopt | BOOLEAN | false | — |
| ducking_strengthopt | FLOAT | 0.250.05–0.9 | Music attenuation factor during speech (relative to current music volume) |
| ducking_fade_msopt | INT | 2000–2000 | — |
| seedopt | INT | 0 | — |
| max_new_tokens_per_lineopt | INT | 2048 | — |
| top_popt | FLOAT | 0.80 | — |
| top_kopt | INT | 20 | — |
| temperatureopt | FLOAT | 1.00 | — |
| repetition_penaltyopt | FLOAT | 1.05 | — |
| soft_limiteropt | BOOLEAN | false | — |
| unload_model_after_generateopt | BOOLEAN | false | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| AUDIO | AUDIO | — |