vox-step-audio-editx
vox-step-audio-editx provides Step-Audio-EditX voice-cloning synthesis for Vox.
Install
pip install vox-step-audio-editx
Runtime Dependencies
The package contains only the Vox adapter. vox pull installs the pinned Step-Audio-EditX inference runtime, including its matching TorchVision package, into $VOX_HOME/runtime/step-audio-editx. The Vox application environment remains the owner of Torch, TorchAudio, Triton, and CUDA runtime libraries.
The supported backend is Linux x86_64 CUDA with at least 10GiB of usable VRAM budget. CPU, ONNX, and Spark/ARM NVIDIA execution are not currently production-supported.
Use with Vox
vox pull step-audio-editx:3b-awq
vox run step-audio-editx:3b-awq "Hello from a cloned voice" --voice /path/to/reference.wav
The model requires reference audio and its transcript. Stored Vox voices provide both through the standard voice API. Inline paralinguistic markers supported by Step-Audio-EditX, such as [Laughter] and [Sigh], may be included in the input text.
1 maintainer
Metadata
1 maintainer
Release files for vox-step-audio-editx 0.1.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vox_step_audio_editx-0.1.9.tar.gz | 8.8 kB | Without provenance | Details for vox_step_audio_editx-0.1.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vox_step_audio_editx-0.1.9-py3-none-any.whl | Python 3 | none | any | Details for vox_step_audio_editx-0.1.9-py3-none-any.whl |
Total release size: 19.6 kB
Release files / vox_step_audio_editx-0.1.9.tar.gz
| Download URL | vox_step_audio_editx-0.1.9.tar.gz |
|---|---|
| Size | 8.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
83f81fa334d36a578fce49a6d264c4910ce52ad19dc022729abc4733986cc6d0
|
|
BLAKE2b-256 checksum How to use checksums |
c4e328020dd162407fd3f7d81394961d68bdf76b3008b28c71bf826ebf2607e1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.0
|
Release files / vox_step_audio_editx-0.1.9-py3-none-any.whl
| Download URL | vox_step_audio_editx-0.1.9-py3-none-any.whl |
|---|---|
| Size | 10.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ae405361cec7e3eb933a4159caefa40e73e367db0e8db518125dff950ba058dc
|
|
BLAKE2b-256 checksum How to use checksums |
d62d2b70d08d5ddec31a22df1c99f594b71b1881db57ad05a34331e76db116b5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.0
|
Security for vox-step-audio-editx 0.1.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
