# MLX Transcribe Tools (/examples/tools/mlx-transcribe-tools)



This recipe targets macOS on Apple silicon, the platform described by [MLX Whisper](https://github.com/ml-explore/mlx-examples/tree/main/whisper). MLX itself also has Linux backends, but installing one alone does not validate this Whisper workflow on Linux.

```python title="mlx_transcribe_tools.py"
"""
MLX Transcribe: A tool for transcribing audio files using MLX Whisper

Requirements:
1. ffmpeg - Install using:
   - macOS: `brew install ffmpeg`
   - Ubuntu: `sudo apt-get install ffmpeg`
   - Windows: Download from https://ffmpeg.org/download.html

2. mlx-whisper library:
   uv pip install mlx-whisper

Example Usage:
- Place your audio files in the 'storage/audio' directory
    Eg: download https://www.ted.com/talks/reid_hoffman_and_kevin_scott_the_evolution_of_ai_and_how_it_will_impact_human_creativity
- Run this script to transcribe audio files
- Supports various audio formats (mp3, mp4, wav, etc.)
"""

from pathlib import Path

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.mlx_transcribe import MLXTranscribeTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


# Get audio files from storage/audio directory
agno_root_dir = Path(__file__).parent.parent.parent.resolve()
audio_storage_dir = agno_root_dir.joinpath("storage/audio")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    if not audio_storage_dir.exists():
        audio_storage_dir.mkdir(exist_ok=True, parents=True)

    agent = Agent(
        name="Transcription Agent",
        model=OpenAIChat(id="gpt-5.6-luna"),
        tools=[MLXTranscribeTools(base_dir=audio_storage_dir)],
        instructions=[
            "To transcribe an audio file, use the `transcribe` tool with the name of the audio file as the argument.",
            "You can find all available audio files using the `read_files` tool.",
        ],
        markdown=True,
    )

    agent.print_response(
        "Summarize the reid hoffman ted talk, split into sections", stream=True
    )
```

Add a real local audio file and change the prompt to name it, for example `Transcribe talk.mp3 and summarize it in sections`. The toolkit does not download the TED webpage as audio. Its default model is `mlx-community/whisper-large-v3-turbo`; the first transcription needs access to download those model weights. The transcription text is passed to the OpenAI model for the summary.

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno mlx-whisper openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

  <Step title="Install ffmpeg">
    On macOS, run `brew install ffmpeg`.
  </Step>

  <Step title="Add an audio file">
    For a standalone file, replace the `agno_root_dir` assignment with `agno_root_dir = Path(__file__).parent.resolve()`. Save the code as `mlx_transcribe_tools.py`, then add the audio file to `storage/audio` beside the script.
  </Step>

  <Step title="Run the example">
    Save the code above as `mlx_transcribe_tools.py`, then run:

    ```bash
    python mlx_transcribe_tools.py
    ```
  </Step>
</Steps>

Full source: [cookbook/91\_tools/mlx\_transcribe\_tools.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/91_tools/mlx_transcribe_tools.py)