Skip to main content
Transcribe Audio turns spoken audio into a text transcript using ElevenLabs Scribe. This node runs on a selectable model and consumes credits when it runs.

​
When to use

  • Generating subtitles or captions
  • Creating searchable transcripts from recordings
  • Feeding spoken content into downstream text nodes

​
Inputs

​
Audio
audio
required
The audio to transcribe. Required. Supports loop mode.

​
Outputs

​
Transcript
text
The transcribed text.

​
Configuration

​
language
string
default:""
ISO 639-1 language code (e.g. en, fr). Leave blank to auto-detect.
​
diarize
boolean
default:false
When enabled, the transcript includes speaker labels (Speaker 1, Speaker 2, …).
​
tag_audio_events
boolean
default:true
When enabled, non-speech sounds such as laughter or applause are tagged in the transcript.

​
Example

Connect an Upload Audio node (or a Generate Speech node) to the Audio input, then wire the Transcript output to a Generate Text node to summarise or reformat the spoken content.
This node runs on a selectable model. See Audio models for supported models and Model settings for available options.