Setup guide for Python

This page shows you how to set up your development environment to use MediaPipe Tasks in your Python applications.

Supported platforms and versions

Building applications with MediaPipe Tasks requires the following development environment resources:

  • OS:
    • Desktop: Windows, Mac, Linux
    • IoT: Raspberry OS 64-bit
  • Python: version 3.8 - 3.11
  • PIP: version 20.3+

Developer environment setup

Before running a MediaPipe task on a Python application, install the MediaPipe package.

$ python -m pip install mediapipe

After installing the package, import it into your development project.

import mediapipe as mp

MediaPipe Tasks dependencies

MediaPipe Tasks provides three prebuilt libraries for vision, text, audio. Depending on the MediaPipe Task used by the app, import the vision, text, or audio library into your development project.

Vision tasks

The MediaPipe Tasks vision module contains tasks that handle image or video inputs. To import the MediaPipe Tasks vision library, import the following dependency to your into your development project.

from mediapipe.tasks.python import vision

Text tasks

The MediaPipe Tasks text module contains tasks that handle string inputs.To import the MediaPipe Tasks text library, import the following dependency to your into your development project.

from mediapipe.tasks.python import text

Audio tasks

The MediaPipe Tasks audio module contains tasks that handle sound inputs. To import the MediaPipe Tasks audio library, import the following dependency to your into your development project.

from mediapipe.tasks.python import audio

BaseOptions configuration

The BaseOptions allow for general configuration of MediaPipe Task APIs.

Option name Description Accepted values
model_asset_buffer The model asset file contents. Model content as a byte string
model_asset_path The path of the model asset to open and map into memory. File path as a string

Troubleshooting

For help with technical questions related to MediaPipe, visit the discussion group or Stack Overflow for support from the community. To report bugs or make feature requests, file an issue on GitHub.

For help setting up your Python development environment, visit the Python developer's guide.