Skip to main content

LiveKit Agent Plugins for Stepfun

Project description

livekit-plugins-stepfun

PyPI version Python 3.9+ License

阶跃星辰服务专用的 LiveKit Agents 插件,提供实时语音交互解决方案。

✨ 特性

  • 实时语音模型 - 支持阶跃星辰实时语音交互
  • 🎤 语音合成 - 支持多种语音选择
  • 🧠 对话生成 - 实时对话处理
  • 📦 开箱即用 - 完整的 Python 包支持

📋 支持的服务

服务 描述 文档链接
Realtime 实时语音模型 阶跃星辰实时语音

🛠️ 安装

使用 pip 安装

pip install livekit-plugins-stepfun

从源码安装

git clone https://github.com/your-repo/livekit-plugins-volcengine.git
cd livekit-plugins-volcengine
pip install -e ./livekit-plugins/livekit-plugins-stepfun

系统要求

  • Python >= 3.9
  • LiveKit Agents >= 1.2.9

⚙️ 配置

环境变量

在使用插件前,请配置以下环境变量:

环境变量 描述 获取方式
STEPFUN_REALTIME_API_KEY 阶跃星辰API密钥 阶跃星辰控制台

.env 文件示例

# .env
STEPFUN_REALTIME_API_KEY=your_stepfun_api_key_here

📖 使用指南

基础使用

from livekit.agents import Agent, AgentSession, JobContext, cli, WorkerOptions
from livekit.plugins import stepfun
from dotenv import load_dotenv

async def entry_point(ctx: JobContext):
    agent = Agent(instructions="You are a helpful assistant.")

    # 使用实时语音模型
    realtime_llm = stepfun.RealtimeModel(
        voice="ganliannvsheng"  # 语音类型
    )

    session = AgentSession(llm=realtime_llm)

    await session.start(agent=agent, room=ctx.room)
    await ctx.connect()

if __name__ == "__main__":
    load_dotenv()
    cli.run_app(WorkerOptions(entrypoint_fnc=entry_point))

高级配置

from livekit.plugins import stepfun

# 高级配置 - 自定义各种参数
realtime_llm = stepfun.RealtimeModel(
    voice="ganliannvsheng",      # 语音类型
    model="step-1o-audio",       # 模型名称
    temperature=0.8,             # 温度
    max_response_output_tokens="inf",  # 最大输出token数
    turn_detection=None,         # 轮次检测
    speed=1.0,                   # 语速
    api_key="your_api_key"       # API密钥 (可选,从环境变量获取)
)

🔧 API 参考

RealtimeModel (实时语音模型)

stepfun.RealtimeModel(
    voice: str = "ganliannvsheng",        # 语音类型
    model: str = "step-1o-audio",         # 模型名称
    temperature: float = 0.8,            # 温度 (0.0-2.0)
    max_response_output_tokens: Union[int, Literal["inf"]] = "inf",  # 最大输出token数
    turn_detection: TurnDetection = None,  # 轮次检测配置
    speed: float = None,                  # 语速
    api_key: str = None,                  # API密钥 (从环境变量获取)
    modalities: list[Literal["text", "audio"]] = ["text", "audio"],  # 输出模态
    http_session: aiohttp.ClientSession = None,  # HTTP会话
    max_session_duration: float = None,   # 最大会话持续时间
    conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS  # 连接选项
)

❓ 常见问题

Q: 如何获取阶跃星辰API密钥?

A: 请访问阶跃星辰平台,注册账号并获取API密钥。

Q: 支持哪些语音类型?

A: 支持多种语音类型,包括:

  • ganliannvsheng - 甘栗女声
  • 其他阶跃星辰支持的语音类型

Q: 如何调整对话参数?

A: 可以通过以下参数调整对话行为:

  • temperature: 控制生成文本的随机性 (0.0-2.0)
  • max_response_output_tokens: 限制输出长度
  • turn_detection: 配置轮次检测行为
  • speed: 调整语音播放速度

Q: 支持哪些模型?

A: 主要支持 step-1o-audio 模型,该模型针对实时语音交互进行了优化。

📝 更新日志

v1.2.9

  • 支持阶跃星辰实时语音模型
  • 支持多种语音类型选择
  • 完善的API文档和使用示例

🤝 贡献

欢迎提交 Issue 和 Pull Request!

  1. Fork 本项目
  2. 创建特性分支 (git checkout -b feature/AmazingFeature)
  3. 提交更改 (git commit -m 'Add some AmazingFeature')
  4. 推送到分支 (git push origin feature/AmazingFeature)
  5. 打开 Pull Request

📄 许可证

本项目采用 Apache 2.0 许可证 - 查看 LICENSE 文件了解详情。

📞 联系我们

🙏 致谢

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

livekit_plugins_stepfun-1.3.0.tar.gz (19.1 kB view details)

Uploaded Source

Built Distribution

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

livekit_plugins_stepfun-1.3.0-py3-none-any.whl (19.2 kB view details)

Uploaded Python 3

File details

Details for the file livekit_plugins_stepfun-1.3.0.tar.gz.

File metadata

  • Download URL: livekit_plugins_stepfun-1.3.0.tar.gz
  • Upload date:
  • Size: 19.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.17 {"installer":{"name":"uv","version":"0.9.17","subcommand":["publish"]},"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}

File hashes

Hashes for livekit_plugins_stepfun-1.3.0.tar.gz
Algorithm Hash digest
SHA256 d61bf202d617c8b6db21f1b24098be4460cd0d6a3a5f76ee834513ee171604bc
MD5 cb85701bc3145346e56987c68819df70
BLAKE2b-256 b72c63342d1af234c52d85c1d8c6c2e60b35fac0825abc6f2346644531cf0256

See more details on using hashes here.

File details

Details for the file livekit_plugins_stepfun-1.3.0-py3-none-any.whl.

File metadata

  • Download URL: livekit_plugins_stepfun-1.3.0-py3-none-any.whl
  • Upload date:
  • Size: 19.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.17 {"installer":{"name":"uv","version":"0.9.17","subcommand":["publish"]},"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}

File hashes

Hashes for livekit_plugins_stepfun-1.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3917bf1f88cbb4261e290d93914e8874ee39df3bd9da0303fec69da1066aaf30
MD5 33a04816649a7c132e46d4282821269c
BLAKE2b-256 d0c4aecbafc82cda9345d0a082103e81668cc0837f5cf45836a6eb2c28adf73f

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