ElevenLabsSpeechToText - ComfyUI Built-in Node Documentation

Complete documentation for the ElevenLabsSpeechToText node in ComfyUI. Learn its inputs, outputs, parameters and usage.

The ElevenLabs Speech to Text node transcribes audio files into text. It uses ElevenLabs’ API to convert spoken words into a written transcript, supporting features like automatic language detection, identifying different speakers, and tagging non-speech sounds like music or laughter.

Inputs

Parameter	Description	Data Type	Required	Range
audio	Audio to transcribe.	AUDIO	Yes	-
model	Model to use for transcription. Selecting this model reveals additional parameters.	COMBO	Yes	"scribe_v2"
tag_audio_events	Annotate sounds like (laughter), (music), etc. in transcript. This parameter is revealed when the "scribe_v2" model is selected. (default: False)	BOOLEAN	No	-
diarize	Annotate which speaker is talking. This parameter is revealed when the "scribe_v2" model is selected. (default: False)	BOOLEAN	No	-
diarization_threshold	Speaker separation sensitivity. Lower values are more sensitive to speaker changes. This parameter is revealed when the "scribe_v2" model is selected and diarize is enabled. (default: 0.22)	FLOAT	No	0.1 - 0.4
temperature	Randomness control. 0.0 uses model default. Higher values increase randomness. This parameter is revealed when the "scribe_v2" model is selected. (default: 0.0)	FLOAT	No	0.0 - 2.0
timestamps_granularity	Timing precision for transcript words. This parameter is revealed when the "scribe_v2" model is selected. (default: “word”)	COMBO	No	"word" "character" "none"
language_code	ISO-639-1 or ISO-639-3 language code (e.g., ‘en’, ‘es’, ‘fra’). Leave empty for automatic detection. (default: "")	STRING	No	-
num_speakers	Maximum number of speakers to predict. Set to 0 for automatic detection. (default: 0)	INT	No	0 - 32
seed	Seed for reproducibility (determinism not guaranteed). (default: 1)	INT	No	0 - 2147483647

Note: The num_speakers parameter cannot be set to a value greater than 0 when the diarize option is enabled. You must either disable diarize or set num_speakers to 0.

Outputs

Output Name	Description	Data Type
text	The transcribed text from the audio.	STRING
language_code	The detected language code of the audio.	STRING
words_json	A JSON-formatted string containing detailed word-level information, including timestamps and speaker labels if enabled.	STRING

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): 7eb5d72615aa8a9e4a8014e45b39cf83dc8d8432d7ce0dccba20489be80a5830