Skip to main content

LLM chat and TTS SDK (with built-in MeloTTS)

Project description

lumanova SDK lumanova 是一个集成大模型智能对话与中文文本转语音(TTS,内置 MeloTTS 算法)的 Python SDK,支持一行开箱调用,便于二次开发和各种场景集成。 安装 确保目录结构如下: Copy lumanova/ ├── lumanova/ # 主 SDK 代码 ├── melotts/ # MeloTTS 代码 ├── setup.py └── README.md 在根目录下运行: Copy pip install .

或开发模式

pip install -e . 快速上手

  1. 智能对话 python Copy from lumanova import Lumanova

client = Lumanova(api_key='your-api-key')

response = client.chat( model="qwen3-max-2026-01-23", messages=[ {"role": "system", "content": "Talk like a pirate."}, {"role": "user", "content": "How do I check if a Python object is an instance of a class? 用中文回答"}, ], ) print(response) api_key:需要在 平台 获取 model:可选模型名称,默认 qwen3.5-plus messages:对话内容(OpenAI 格式)、支持多角色多轮 2. 文本转语音(TTS) python Copy from lumanova import LumaTTS

tts = LumaTTS(device='cpu') audio_file = tts.tts("你好,世界!", output_path='hello.wav') print(f"音频已保存至: {audio_file}") device 默认为 "cpu",Mac M1/M2 可尝试 "mps" output_path 输出音频路径,可自定义文件名 典型结构 Lumanova:对话 API,直连模型服务 LumaTTS:文本转语音接口,构造实例后可多次快速生成音频 常见问题 权重加载慢? TTS 模型首次加载需联网下载权重,之后本地缓存,合成速度极快。 只需随 SDK 一起 pip 安装,无额外依赖。 如遇到 API Key 配置异常或网络问题,可参考错误提示排查。 License MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lumanova-0.0.1.post5.tar.gz (4.6 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lumanova-0.0.1.post5-py3-none-any.whl (4.8 MB view details)

Uploaded Python 3

File details

Details for the file lumanova-0.0.1.post5.tar.gz.

File metadata

  • Download URL: lumanova-0.0.1.post5.tar.gz
  • Upload date:
  • Size: 4.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.23

File hashes

Hashes for lumanova-0.0.1.post5.tar.gz
Algorithm Hash digest
SHA256 934caedcc3adbfd80efdd16f782eaa7828b653ddf9ddcb83a86f56081ecfc61e
MD5 ad5df6a597f4658e2a1b02f1833f4a97
BLAKE2b-256 fffe75e0a22208d39d54d078035d95e7a673b2bf13b90bb467567b7a96e7406e

See more details on using hashes here.

File details

Details for the file lumanova-0.0.1.post5-py3-none-any.whl.

File metadata

  • Download URL: lumanova-0.0.1.post5-py3-none-any.whl
  • Upload date:
  • Size: 4.8 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.23

File hashes

Hashes for lumanova-0.0.1.post5-py3-none-any.whl
Algorithm Hash digest
SHA256 5de40d76d497ff32da8596f74ee378a833e910752b184e40772398e936085a6e
MD5 eb82b04380db62b37b7334584bc4dcd3
BLAKE2b-256 86e3893ecee5e42e40eb84427d221f8f4dc75f3c0b4ee04d165cb34d408ca763

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page