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
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 vox_step_audio_editx-0.1.3.tar.gz.
File metadata
- Download URL: vox_step_audio_editx-0.1.3.tar.gz
- Upload date:
- Size: 8.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.13.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1503ad59f7476b9c39c03670a53e4590ef70bfe91af8c9fce25b83329ca6ba87
|
|
| MD5 |
e8bb2ba07cbf5a5746b17915978c421c
|
|
| BLAKE2b-256 |
e24dbff39815715c98613c3a827abfc8c80b0b3318d15e9edacd88bba144cd92
|
File details
Details for the file vox_step_audio_editx-0.1.3-py3-none-any.whl.
File metadata
- Download URL: vox_step_audio_editx-0.1.3-py3-none-any.whl
- Upload date:
- Size: 10.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.13.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0fdf09868410fffba954ce6d1eb9f18f22e0fa54a88a40bc0423bfe2f92f7864
|
|
| MD5 |
61f1fb1cafa95e50bdf14bd2348c314e
|
|
| BLAKE2b-256 |
10c14fea314d775fef94a60dfcb10e67196198aad25572e0581b0a43c8eaad82
|
