# AzureOpenAITranscriptionsTool

> **Class** in `langchain_azure_ai`

📖 [View in docs](https://reference.langchain.com/python/langchain-azure-ai/tools/_openai_tools/AzureOpenAITranscriptionsTool)

Transcribes audio to text using an OpenAI-compatible speech-to-text API.

This tool connects to model deployments in Azure AI Foundry or Azure OpenAI that
expose an OpenAI-compatible ``/audio/transcriptions`` endpoint, such as
``whisper-1`` or a custom Whisper deployment.

Supports both local audio files and remote URLs. Automatically detects the source
type and downloads remote files as needed. Supports a wide range of audio formats
including MP3, MP4, MPEG, MPGA, M4A, OGG, FLAC, and WAV.

## Signature

```python
AzureOpenAITranscriptionsTool()
```

## Description

**Example:**

.. code-block:: python

from langchain_azure_ai.tools import AzureOpenAITranscriptionsTool

tool = AzureOpenAITranscriptionsTool(
    endpoint="https://<resource>.openai.azure.com/openai/v1/",
    credential="<api-key>",
    model="whisper-1",
)
result = tool.invoke({"audio_path": "path/to/audio.wav"})

## Extends

- `BaseTool`
- `ModelInferenceService`

## Properties

- `name`
- `description`
- `args_schema`
- `model`

## Methods

- [`initialize_client()`](https://reference.langchain.com/python/langchain-azure-ai/tools/_openai_tools/AzureOpenAITranscriptionsTool/initialize_client)

---

[View source on GitHub](https://github.com/langchain-ai/langchain-azure/blob/7a6a664d617264df8dcb12fcfb1bacc09f21d504/libs/azure-ai/langchain_azure_ai/tools/_openai_tools.py#L222)