phantom-audio-separation
Demucs-based stem separation plugin for phantom-audio.
Splits a stereo mix into individual stems (vocals, drums, bass, other) using
Meta's Hybrid Transformer Demucs model. This package carries the heavyweight
PyTorch + Demucs dependency tree (~2.5 GB) so the core phantom-audio
analysis library stays lean and independent of PyTorch's release cadence and
platform-support matrix.
Install
# Recommended: via the phantom-audio meta-extra
uv tool install "phantom-audio[separation]" --python 3.13
# Or directly
uv pip install phantom-audio-separation
Usage
Once installed, phantom-audio discovers this plugin automatically through
the phantom.separation entry-point group -- no configuration needed. The
existing APIs keep working unchanged:
from phantom import separate_stems
result = separate_stems("mix.wav", "./stems")
print(result.stems) # {"vocals": ".../vocals.wav", "drums": ..., ...}
Or from the CLI / MCP server:
phantom separate mix.wav --output ./stems/
phantom doctor reports phantom-audio-separation as OK only when the
plugin is installed and importable.
Note: First use downloads the htdemucs model (~80 MB). Subsequent calls use the cached model.
License
AGPL-3.0-or-later, same as phantom-audio. See the repository LICENSE.
1 maintainer
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 phantom_audio_separation-1.5.0.tar.gz.
File metadata
- Download URL: phantom_audio_separation-1.5.0.tar.gz
- Upload date:
- Size: 7.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ad126c348e0f3f787da0fe1ec9b00f750b048f3539cff7c16de5251df282e91b
|
|
| MD5 |
bd78c6ffc8617225425ae51270ca0cb6
|
|
| BLAKE2b-256 |
4bdaa191a4be3babc8935a5d2a51618578b1acb18f08e2fbae1fb111f70ee56f
|
File details
Details for the file phantom_audio_separation-1.5.0-py3-none-any.whl.
File metadata
- Download URL: phantom_audio_separation-1.5.0-py3-none-any.whl
- Upload date:
- Size: 5.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
95bdf3ca7426b5e0b072c8cb20428aaa619d5e3036e468e7d0a270e483a89b09
|
|
| MD5 |
8aa966ca3bb4bd8247be1bcae7632310
|
|
| BLAKE2b-256 |
d7ef6348ac5a8d9506036428f8980b778df41c07707be71e2f2e7154b95f1412
|
