On-device speech transcription for macOS via Apple's SpeechAnalyzer
Project description
mac-speech-analyzer
🐍 Python package to run the macOS 26 SpeechAnalyzer API from Python to transcribe audio files.
The SpeechAnalyzer API generally provides faster and better results than other locally running transcription engines of comparable size.
Features
- Online or Offline transcription
- Automatic download of new languages
Requirements
- macOS >= 26.0
- XCode command-line tools
Installation
mac-speech-analyzer is currently not tracked on pypi yet.
uv add git+https://github.com/paraversal/mac-speech-analyzer
# or
pip install git+https://github.com/paraversal/mac-speech-analyzer
Usage
Basic usage
from macspeechanalyzer import transcribe
text = transcribe("/path/to/file", locale = "en_US")
Technical details
This package is made up of two parts: the Python wrapper provides the API, but the actual functionality is achieved by embedding a Swift project which exposes functions to C. With this kind of three language interplay, a clean separation of concerns is really important. Therefore, the implementation is divided into the following four layers:
- Pure Python
- Python → C compat
- Swift → C compat
- Pure Swift
The pure Swift and pure Python layers only deal with their respective languages & types, while the compat layers do all the ugly work of converting between native and C-compatible types
Roadmap
- ✅ Basic one-shot transcription
- Class-based interface
- Context manager implementation
- Transcription of live audio stream (microphone, ...)
Development
uv pip install -e .
to one-time-install the package as editable, from then on:
ninja
to rebuild the package
License
mac-speech-analyzer is released under the MIT License. See LICENSE for more details.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mac_speech_analyzer-0.1.0.tar.gz.
File metadata
- Download URL: mac_speech_analyzer-0.1.0.tar.gz
- Upload date:
- Size: 19.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.11.29 {"installer":{"name":"uv","version":"0.11.29","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e3fded39cf3bc5851e49a4a9804dafb403483d0f31feefce418917f9cb0b0f9a
|
|
| MD5 |
2ff13d2dd258a1bb4cf58593863dda00
|
|
| BLAKE2b-256 |
a8434d9bb03166d52b3599e51e8fea7c43d664e179168004531b4767d01cb86e
|
File details
Details for the file mac_speech_analyzer-0.1.0-py3-none-macosx_26_0_arm64.whl.
File metadata
- Download URL: mac_speech_analyzer-0.1.0-py3-none-macosx_26_0_arm64.whl
- Upload date:
- Size: 19.4 kB
- Tags: Python 3, macOS 26.0+ ARM64
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.11.29 {"installer":{"name":"uv","version":"0.11.29","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
81ad0e60532af536395f2813be3ca7c17881ce0c73134c20792be6e4ce75ced5
|
|
| MD5 |
cf49674cd9ef7846011fbba137a91707
|
|
| BLAKE2b-256 |
901945758512d83eefb4e33ed4020209907571c10e5ac2bd80ff1aa5236dedc7
|
