> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orisu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcribe Audio

> Convert spoken audio to text using a speech-to-text model.

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

<ParamField body="Audio" type="audio" required>
  The audio to transcribe. Required. Supports loop mode.
</ParamField>

## Outputs

<ParamField body="Transcript" type="text">
  The transcribed text.
</ParamField>

## Configuration

<ParamField body="language" type="string" default="">
  ISO 639-1 language code (e.g. `en`, `fr`). Leave blank to auto-detect.
</ParamField>

<ParamField body="diarize" type="boolean" default={false}>
  When enabled, the transcript includes speaker labels (Speaker 1, Speaker 2, …).
</ParamField>

<ParamField body="tag_audio_events" type="boolean" default={true}>
  When enabled, non-speech sounds such as laughter or applause are tagged in the transcript.
</ParamField>

## 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.

<Note>
  This node runs on a selectable model. See [Audio models](/models/audio) for supported models and [Model settings](/models/settings) for available options.
</Note>