Supertonic MNN
English
Supertonic MNN is a high-performance, lightweight text-to-speech (TTS) library based on MNN. It supports both command-line interface (CLI) and Python API, making it easy to integrate into your projects.
Features
- Fast Inference: RTF ~ 0.07 on CPU.
- Lightweight: Minimal dependencies.
- Supported Precisions: fp32, fp16, int8.
Available Voices
- M1: Male voice 1
- M2: Male voice 2
- F1: Female voice 1
- F2: Female voice 2
Documentation
Full documentation is available at Supertonic MNN Docs.
Installation
pip install supertonic-mnn
Quick Usage
CLI
echo "Hello world" | supertonic-mnn -o hello.wav
Python API
from supertonic_mnn import SupertonicTTS
# 1. Initialize
tts = SupertonicTTS()
# 2. Synthesize
# Models will be downloaded automatically if not present
audio, sample_rate = tts.synthesize("Hello world", voice="M1", output_file="hello.wav")
See examples/ for more details.
Acknowledgments
This project is based on the original Supertonic by Supertone Inc.
中文
Supertonic MNN 是一个基于 MNN 的高性能、轻量级文本转语音 (TTS) 库。它同时支持命令行接口 (CLI) 和 Python API,方便您将其集成到项目中。
特性
- 极速推理: CPU 上 RTF 约为 0.07。
- 轻量级: 依赖极少。
- 多精度支持: fp32, fp16, int8。
可用音色
- M1: 男声 1
- M2: 男声 2
- F1: 女声 1
- F2: 女声 2
文档
完整文档请访问 Supertonic MNN 文档。
安装
pip install supertonic-mnn
快速上手
命令行 (CLI)
echo "你好,世界" | supertonic-mnn -o hello.wav
Python API
from supertonic_mnn import SupertonicTTS
# 1. 初始化
tts = SupertonicTTS()
# 2. 推理
# 如果模型不存在,会自动下载
audio, sample_rate = tts.synthesize("你好,世界", voice="M1", output_file="hello.wav")
更多详情请参阅 examples/ 目录。
致谢
本项目基于 Supertone Inc. 的原始 Supertonic 工作。
Metadata
Release files for supertonic-mnn 0.1.3
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 |
|---|---|---|---|---|
| supertonic_mnn-0.1.3.tar.gz | 80.8 kB | Without provenance | Details for supertonic_mnn-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| supertonic_mnn-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for supertonic_mnn-0.1.3-py3-none-any.whl |
Total release size: 93.4 kB
Release files / supertonic_mnn-0.1.3.tar.gz
| Download URL | supertonic_mnn-0.1.3.tar.gz |
|---|---|
| Size | 80.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d922df947fbf1de2edc78d3c7304e492404beee78a074c4af54985431348c101
|
|
BLAKE2b-256 checksum How to use checksums |
ae0c9654b312afaeafe9338331ebfd2840448ff141c88750e62b2d529a60aa26
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"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 / supertonic_mnn-0.1.3-py3-none-any.whl
| Download URL | supertonic_mnn-0.1.3-py3-none-any.whl |
|---|---|
| Size | 12.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c3b708b8321ab355b535acdebc6e05172203f2d2c26a4fc8cc3988f9723a9465
|
|
BLAKE2b-256 checksum How to use checksums |
abe5ee06bcc429fede0e9ef714ba7411a87fae9042035137cbc121e5fd658355
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"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}
|
Security for supertonic-mnn 0.1.3
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.