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
Metadata
1 maintainer
Release files for phantom-audio-separation 1.5.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| phantom_audio_separation-1.5.0.tar.gz | 7.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| phantom_audio_separation-1.5.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 13.0 kB
Release files / phantom_audio_separation-1.5.0.tar.gz
| Download URL | phantom_audio_separation-1.5.0.tar.gz |
|---|---|
| Size | 7.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ad126c348e0f3f787da0fe1ec9b00f750b048f3539cff7c16de5251df282e91b
|
|
BLAKE2b-256 checksum How to use checksums |
4bdaa191a4be3babc8935a5d2a51618578b1acb18f08e2fbae1fb111f70ee56f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is 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}
|
Release files / phantom_audio_separation-1.5.0-py3-none-any.whl
| Download URL | phantom_audio_separation-1.5.0-py3-none-any.whl |
|---|---|
| Size | 5.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
95bdf3ca7426b5e0b072c8cb20428aaa619d5e3036e468e7d0a270e483a89b09
|
|
BLAKE2b-256 checksum How to use checksums |
d7ef6348ac5a8d9506036428f8980b778df41c07707be71e2f2e7154b95f1412
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is 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}
|
