ElevenLabsTextToDialogue - ComfyUI Built-in Node Documentation - ComfyUI

The ElevenLabs Text to Dialogue node generates a multi-speaker audio dialogue from text. It allows you to create a conversation by specifying different text lines and distinct voices for each participant. The node sends the dialogue request to the ElevenLabs API and returns the generated audio.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
`stability`	Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech. (default: 0.5)	FLOAT	Yes	0.0 - 1.0
`apply_text_normalization`	Text normalization mode. ‘auto’ lets the system decide, ‘on’ always applies normalization, ‘off’ skips it.	COMBO	Yes	`"auto"` `"on"` `"off"`
`model`	Model to use for dialogue generation (default: `"eleven_v4"`).	COMBO	Yes	`"eleven_v3"` `"eleven_v4"` `"eleven_v4_turbo"`
`inputs`	Number of dialogue entries. Selecting a number creates that many text and voice input pairs.	DYNAMIC_COMBO	Yes	`"1"` `"2"` `"3"` `"4"` `"5"` `"6"` `"7"` `"8"` `"9"` `"10"`
`language_code`	ISO 639-1 language code (e.g., ‘en’, ‘es’, ‘ja’). Leave empty for automatic detection. (default: empty)	STRING	Yes	-
`seed`	Seed for reproducibility. (default: 1)	INT	Yes	0 - 4294967295
`output_format`	Audio output format.	COMBO	Yes	`"mp3_44100_192"` `"opus_48000_192"`

Dialogue Entry Inputs

Shared by all inputs options.

Parameter	Description	Data Type	Required	Range
`text1` … `text10`	Text content for the corresponding dialogue entry. The node creates one `text` field for each selected dialogue entry. Each text value must contain at least one character.	STRING	Yes	-
`voice1` … `voice10`	Voice for the corresponding dialogue entry. Connect from a Voice Selector or Instant Voice Clone node. The node creates one `voice` field for each selected dialogue entry.	ELEVENLABS_VOICE	Yes	-

Note: The inputs selector can create up to 10 dialogue entries. Each entry requires both a text field and a voice field. The text value cannot be empty. The voice input expects a voice ID provided by a compatible ElevenLabs voice node.

Outputs

Output Name	Description	Data Type
`audio`	The generated multi-speaker dialogue audio in the selected output format.	AUDIO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): bff737be0c828990d7286de4372e995295a4716febd388d7cc02c2a9987a6c80