HeyGenVoiceTextToSpeechNode - ComfyUI Built-in Node Documentation - ComfyUI

Speak text in a voice cloned with HeyGen Voice 1.0 Instant Clone. The node sends the text and the voice ID to HeyGen and returns the generated speech as audio. Two models are available: heygen-voice-1 and the cheaper, faster heygen-voice-1-turbo. Selecting a model reveals the parameters specific to that model.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	Model to use. `heygen-voice-1-turbo` is faster and costs less. Selecting a model reveals the parameters specific to it: `voice_id`, `text`, `language`, and `expressiveness_boost`.	DYNAMIC_COMBO	Yes	`"heygen-voice-1"` `"heygen-voice-1-turbo"`
`voice_id`	Voice from HeyGen Voice 1.0 Instant Clone (default: empty).	STRING	Yes	N/A
`text`	Text to speak. Up to 5000 characters; speech longer than about 12 minutes fails, so split very long Chinese or Japanese text (default: empty).	STRING	Yes	1 to 5000 characters
`language`	Language of the text. Set it for closely related languages such as Serbian or Malay, which auto-detection can confuse (default: “auto”).	COMBO	Yes	`"auto"` Multiple language presets
`expressiveness_boost`	Higher values are more expressive; lower values stay closer to the original voice (default: 0.5).	FLOAT	Yes	0.0 to 1.0 (step 0.05)

Note: voice_id must be a voice created by HeyGen Voice 1.0 Instant Clone; the node stops with an error when it is empty. text must contain at least one character.

Outputs

Output Name	Description	Data Type
`AUDIO`	The speech generated from the text, spoken in the cloned voice.	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): 936cb63237681779dd4d9a74d048afae93160638d069be6b16e5855d333e584a