onnxvoice
onnxvoice manages, verifies, stores, and executes ONNX voice-model assets through shared catalogs, a content-addressed cache, and a common Python API.
It is a model asset and runtime layer, not a complete text-to-speech frontend. Text normalization, G2P/phonemization, sentence planning, and higher-level voice policy belong to producer packages.
Install
The base package does not install ONNX Runtime. Install the provider extra for the target system:
python -m pip install onnxvoice
python -m pip install "onnxvoice[cpu]"
python -m pip install "onnxvoice[gpu]"
python -m pip install "onnxvoice[directml]"
python -m pip install "onnxvoice[openvino]"
For Pocket's optional Hugging Face voice-state downloads, add the pocket extra. See Pocket download setup.
Quick start
CLI
onnxvoice list --kind voice --lang en-US
onnxvoice install piper:en_US-lessac-medium
onnxvoice installed
onnxvoice cache info
Python
from onnxvoice import OnnxVoice
voice = OnnxVoice()
installation = voice.install("piper:en_US-lessac-medium")
runtime = voice.open(installation, provider="cpu")
try:
# Supply model-ready token IDs from your frontend.
result = runtime.infer([1, 20, 14, 5, 2])
print(result.audio.shape, result.sample_rate)
finally:
runtime.close()
install() acquires catalog assets. open() uses an existing managed installation and does not download assets. open_local() opens explicit files without copying or registering them.
Supported systems
| System | Built-in adapter | Catalog | Stable voice selectors |
|---|---|---|---|
| Piper | Yes | Yes | Yes |
| Kokoro | Yes | Yes | Yes |
| Yes | Yes | Conditional on explicit voice-state identity metadata | |
| Supertonic | Yes | Yes | No |
Adapters execute system-specific model contracts. They do not imply text normalization or phonemization support. The selector registry and catalogs are independent capabilities.
Documentation
The full documentation includes task-oriented CLI and Python guides, storage and update behavior, provider setup, local-model workflows, per-system runtime contracts, and the API reference.
Development
python -m pip install -e ".[dev,cpu]"
pytest -q
python docs/make.py html
License
The source code is Apache-2.0. Downloaded models, voices, and model cards retain their own licenses and terms. Installing an asset through onnxvoice does not relicense it.
1 maintainer
Metadata
1 maintainer
Release files for onnxvoice 0.1.13
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| onnxvoice-0.1.13.tar.gz | 398.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| onnxvoice-0.1.13-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 522.7 kB
Release files / onnxvoice-0.1.13.tar.gz
| Download URL | onnxvoice-0.1.13.tar.gz |
|---|---|
| Size | 398.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
02e7a51ef6827a7143f6807022bacc04ef00e7ab05e8dcb3c8be3e6fda8fc801
|
|
BLAKE2b-256 checksum How to use checksums |
e621e3fc3d182fcdb27227d8c45f6d2d6a75e3b0deb0393e3b03b0ad2abff0af
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Release files / onnxvoice-0.1.13-py3-none-any.whl
| Download URL | onnxvoice-0.1.13-py3-none-any.whl |
|---|---|
| Size | 124.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c226d60129b4d5a266e691e3450fdc2952f46fba6692bd49e4ed0b02a3dff610
|
|
BLAKE2b-256 checksum How to use checksums |
5df4b61651a3cedbf63a6853ff4358ee574c555c78fd2c4dad74a6cfc7a37bfe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
