AIIA Dialogue TTS (Multi-Role) is a ComfyUI node in the AIIA/Podcast category from ComfyUI_AIIA. Inputs: dialogue_json, tts_engine, pause_duration…

Tired of OOM errors and tedious file management? The AIIA Node Suite delivers the ultimate workflow overhaul, headlined by the AIIA Media Browser: a high-performance file hub fully integrated into ComfyUI. Instantly preview images, videos, and audio, and experience ultimate smoothness thanks to smart caching and virtual scrolling, even with tens of thousands of files. It also features a powerful fullscreen viewer, rich tooltip previews, and flexible sorting. Alongside the browser, our Video Combine node fundamentally solves memory bottlenecks in long video generation. By streaming frames from disk, you can create videos of virtually unlimited length, making OOM errors a thing of the past. The suite also includes OOM-safe FLOAT video generation, advanced audio processing, and other utilities, providing a complete end-to-end solution from content creation to asset management.

ComfyUI_AIIA

dialogue_json

tts_engine

pause_duration

speed_global

batch_mode

speaker_A_ref

speaker_A_id

speaker_A_emotion

speaker_A_dialect

speaker_B_ref

speaker_B_id

speaker_B_emotion

speaker_B_dialect

speaker_C_ref

speaker_C_id

speaker_C_emotion

speaker_C_dialect

cosyvoice_model

vibevoice_model

qwen_model

max_batch_char

cfg_scale

temperature

top_k

top_p

AIIA_Dialogue_TTS

full_audio

segments_info

AIIA Dialogue TTS (Multi-Role)

Name	Type	Default	Description
dialogue_json	STRING		—
tts_engine	COMBO	CosyVoice	3 options: CosyVoice, VibeVoice, Qwen3-TTS
pause_duration	FLOAT	0.50–5	—
speed_global	FLOAT	1.000.5–2	—
batch_mode	COMBO	Natural (Hybrid)	3 options: Natural (Hybrid), Strict (Per-Speaker), Whole (Single Batch)
speaker_A_refopt	AUDIO		—
speaker_A_idopt	STRING		—
speaker_A_emotionopt	COMBO	None	44 options: None, Happy (开心), Sad (悲伤), Angry (愤怒), Excited (兴奋), Gentle (温柔), +38
speaker_A_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
speaker_B_refopt	AUDIO		—
speaker_B_idopt	STRING		—
speaker_B_emotionopt	COMBO	None	44 options: None, Happy (开心), Sad (悲伤), Angry (愤怒), Excited (兴奋), Gentle (温柔), +38
speaker_B_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
speaker_C_refopt	AUDIO		—
speaker_C_idopt	STRING		—
speaker_C_emotionopt	COMBO	None	44 options: None, Happy (开心), Sad (悲伤), Angry (愤怒), Excited (兴奋), Gentle (温柔), +38
speaker_C_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
cosyvoice_modelopt	COSYVOICE_MODEL		—
vibevoice_modelopt	VIBEVOICE_MODEL		—
qwen_modelopt	QWEN_MODEL		—
max_batch_charopt	INT	1000100–32768	—
cfg_scaleopt	FLOAT	1.51–10	—
temperatureopt	FLOAT	0.800.1–2	—
top_kopt	INT	200–100	—
top_popt	FLOAT	0.950–1	—

Name	Type	Description
full_audio	AUDIO	—
segments_info	STRING	—

AIIA Dialogue TTS (Multi-Role)

Inputs (25)

Outputs (2)