---
title: "Automatic Speech Recognition"
description: "Local-first visual environment for building and running AI workflows. Build agents visually, deploy anywhere, privacy by design."
canonical: https://docs.nodetool.ai/nodes/nodetool/text/automaticspeechrecognition
markdown: https://docs.nodetool.ai/nodes/nodetool/text/automaticspeechrecognition.md
product: NodeTool
source: https://github.com/nodetool-ai/nodetool/blob/main/docs/nodes/nodetool/text/automaticspeechrecognition.md
---

# Automatic Speech Recognition

**Type:** `nodetool.text.AutomaticSpeechRecognition`

**Namespace:** `nodetool.text`

## Description

Transcribe audio to text using automatic speech recognition models.
    audio, speech, recognition, transcription, ASR, whisper

## Properties

| Property | Type | Description | Default |
|----------|------|-------------|---------|
| model | `asr_model` |  | `{"type":"asr_model","provider":"fal_ai","id":"o...` |
| audio | `audio` | The audio to transcribe | `{"type":"audio","uri":"","asset_id":null,"data"...` |
| language | `str` | Language of the audio (ISO 639-1 code, empty for auto-detect) | `` |
| prompt | `str` | Optional prompt to guide the transcription | `` |
| temperature | `float` | Sampling temperature for the transcription model | `0` |

## Outputs

| Output | Type | Description |
|--------|------|-------------|
| text | `str` |  |

## Related Nodes

Browse other nodes in the [nodetool.text](./) namespace.