Transcribe

Convert spoken audio to text with optional speaker diarization and audio event tagging.

Overview

The Transcribe node uses ElevenLabs Speech-to-Text to convert audio into a text transcript. It supports automatic language detection or explicit language selection, speaker diarization (identifying who said what), and audio event tagging (labeling non-speech sounds like music, laughter, or applause). The output includes the full transcript text as well as per-segment results with timestamps.

Configuration

Field Type Default Description
Provider TranscribeProvider "elevenlabs-stt" Transcription engine
Language string "auto" Language code for the audio, or “auto” for automatic detection. Supports 20+ languages
Speaker Diarization boolean false When enabled, identifies and labels different speakers in the transcript
Tag Audio Events boolean false When enabled, annotates non-speech audio events (music, laughter, applause, etc.) in the transcript

Inputs & Outputs

Output Details

The node produces both a simple text output and structured result data:

Field Type Description
generatedText string The full transcript as plain text
generatedResults array Array of result objects, each containing text, language, jobId, and timestamp

When Speaker Diarization is enabled, the transcript includes speaker labels (e.g., “Speaker 1:”, “Speaker 2:”) before each segment.

When Tag Audio Events is enabled, non-speech sounds are annotated inline (e.g., “[music]”, “[laughter]”).

Best Practices

Common Use Cases

Tips