---
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/huggingface/automaticspeechrecognition
markdown: https://docs.nodetool.ai/nodes/huggingface/automaticspeechrecognition.md
product: NodeTool
source: https://github.com/nodetool-ai/nodetool/blob/main/docs/nodes/huggingface/automaticspeechrecognition.md
---

# Automatic Speech Recognition

**Type:** `huggingface.AutomaticSpeechRecognition`

**Namespace:** `huggingface`

## Properties

| Property | Type | Description | Default |
|----------|------|-------------|---------|
| model | `str` | Automatic-speech-recognition model repo id. | `openai/whisper-large-v3` |
| audio | `audio` | The audio to transcribe. | - |
| return_timestamps | `bool` | Also return per-chunk timestamps. | `false` |

## Outputs

| Output | Type | Description |
|--------|------|-------------|
| output | `str` |  |
| chunks | `list` |  |

## Related Nodes

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