OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Basic Pitch

Basic Pitch is a Python library for automatic music transcription that uses a lightweight neural network to convert compatible audio files into MIDI, including pitch bends and predicted note events. It supports multipitch and polyphonic instruments and provides command-line and Python interfaces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Basic Pitch — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Basic Pitch when a music-audio file needs to become MIDI or note-event data for further editing or processing, especially when pitch bends and polyphonic transcription matter.

Who it is for

  • Musicians and researchers converting recorded music into editable MIDI.
  • Developers adding audio-to-MIDI transcription to Python audio-processing workflows.
  • Users processing one audio file or batches of files through a command-line interface.

Documented uses

  • Convert a compatible music recording into a MIDI file with pitch bends.
  • Transcribe several audio files in one command-line run.
  • Retrieve model outputs, MIDI data and note events from Python code.
  • Save optional WAV renderings, raw model output or note events in additional formats.
Before you choose

Requirements & limits

The library is open source under the Apache-2.0 license and can be installed from PyPI. The repository documents macOS, Windows and Ubuntu support with Python 3.7–3.11; Mac M1 hardware is documented for Python 3.10.

  • The tool returns a MIDI interpretation, not a completed musical arrangement.
  • The project supports polyphonic instruments but says performance is best with one instrument at a time.
  • Model runtimes include TensorFlow, CoreML, TensorFlow Lite and ONNX; default runtime selection varies by platform.
  • The Python interface returns raw model output, MIDI data and note events, while CLI flags enable optional WAV, NPZ and CSV outputs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Basic Pitch and transcribe audio from the command line

Install the Python package and generate a MIDI transcription from a compatible audio file.

Before you start

  • macOS, Windows or Ubuntu
  • Python 3.7, 3.8, 3.9, 3.10 or 3.11
  • A compatible audio file and an output directory

Steps

  1. Install the package with the command below.

    Documented command
    pip install basic-pitch

  2. Run basic-pitch .

  3. For multiple files, add their input paths to the same command; optionally add documented flags to save WAV, NPZ or CSV outputs.

Expected outcome

A MIDI transcription is saved in the chosen output directory; optional formats can also be saved when their flags are used.

Guide limitations

  • Basic Pitch works best on one instrument at a time.
  • On Mac M1 hardware, the documented supported Python version is 3.10.
  • Runtime availability varies by platform and package configuration.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
spotify/basic-pitch · Official homepage title · retained in its source language
How we review sourcesSuggest a correction