livekit-plugins-tencent
腾讯云服务专用的 LiveKit Agents 插件,提供语音识别集成解决方案。
✨ 特性
- 🎤 语音识别 (STT) - 支持腾讯云语音识别服务
- 🔒 安全认证 - 支持腾讯云标准的密钥认证方式
- 📦 开箱即用 - 完整的 Python 包支持
📋 支持的服务
| 服务 | 描述 | 文档链接 |
|---|---|---|
| STT | 语音识别 | 腾讯云语音识别 |
🛠️ 安装
使用 pip 安装
pip install livekit-plugins-tencent
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-tencent
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 |
|---|---|---|
TENCENT_STT_APP_ID |
腾讯云应用ID | 腾讯云控制台 |
TENCENT_STT_SECRET_KEY |
腾讯云密钥 | 腾讯云控制台 |
TENCENT_STT_ID |
腾讯云Secret ID | 腾讯云控制台 |
.env 文件示例
# .env
TENCENT_STT_APP_ID=your_app_id
TENCENT_STT_SECRET_KEY=your_secret_key
TENCENT_STT_ID=your_secret_id
📖 使用指南
基础使用
from livekit.agents import Agent, AgentSession, JobContext, cli, WorkerOptions
from livekit.plugins import tencent
from dotenv import load_dotenv
async def entry_point(ctx: JobContext):
agent = Agent(instructions="You are a helpful assistant.")
session = AgentSession(
# 语音识别 - 参数可从腾讯云控制台获取
stt=tencent.STT(
app_id="your_app_id",
secret_key="your_secret_key",
secret_id="your_secret_id"
)
)
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 tencent
# 自定义STT配置
stt = tencent.STT(
app_id="your_app_id", # 应用ID
secret_key="your_secret_key", # 密钥
secret_id="your_secret_id", # Secret ID
region="ap-beijing", # 地域 (默认: ap-beijing)
engine_model_type="16k_zh", # 引擎模型类型
voice_format="wav", # 音频格式
filter_dirty=1, # 是否过滤脏话 (0: 不过滤, 1: 过滤)
filter_modal=1, # 是否过滤语气词 (0: 不过滤, 1: 过滤)
convert_num_mode=1 # 数字转换模式 (0: 不转换, 1: 转换为阿拉伯数字)
)
🔧 API 参考
STT (语音识别)
tencent.STT(
app_id: str, # 应用ID
secret_key: str, # 密钥
secret_id: str, # Secret ID
region: str = "ap-beijing", # 地域
engine_model_type: str = "16k_zh", # 引擎模型类型
voice_format: str = "wav", # 音频格式
filter_dirty: int = 1, # 是否过滤脏话
filter_modal: int = 1, # 是否过滤语气词
convert_num_mode: int = 1 # 数字转换模式
)
❓ 常见问题
Q: 如何获取腾讯云的认证信息?
A: 请访问腾讯云控制台,创建语音识别应用并获取以下信息:
- App ID: 应用ID
- Secret Key: 密钥
- Secret ID: Secret ID
Q: 支持哪些音频格式?
A: 支持多种音频格式,包括:
wav- WAV格式mp3- MP3格式m4a- M4A格式- 其他腾讯云支持的音频格式
Q: 如何配置语音识别参数?
A: 可以通过以下参数优化识别效果:
engine_model_type: 选择合适的引擎模型 (16k_zh, 8k_zh等)filter_dirty: 过滤敏感词汇filter_modal: 过滤语气词convert_num_mode: 数字转换设置
Q: 支持哪些地域?
A: 支持腾讯云的各个地域,包括:
ap-beijing- 北京ap-shanghai- 上海ap-guangzhou- 广州- 其他腾讯云支持的地域
📝 更新日志
v1.2.9
- 支持腾讯云语音识别服务
- 支持多种音频格式和地域
- 完善的API文档和使用示例
🤝 贡献
欢迎提交 Issue 和 Pull Request!
- Fork 本项目
- 创建特性分支 (
git checkout -b feature/AmazingFeature) - 提交更改 (
git commit -m 'Add some AmazingFeature') - 推送到分支 (
git push origin feature/AmazingFeature) - 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
- 项目主页: GitHub
- 问题反馈: Issues
- 邮箱: 790990241@qq.com
🙏 致谢
Metadata
Release files for livekit-plugins-tencent 1.3.0
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 |
|---|---|---|---|---|
| livekit_plugins_tencent-1.3.0.tar.gz | 9.0 kB | Without provenance | Details for livekit_plugins_tencent-1.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| livekit_plugins_tencent-1.3.0-py3-none-any.whl | Python 3 | none | any | Details for livekit_plugins_tencent-1.3.0-py3-none-any.whl |
Total release size: 17.8 kB
Release files / livekit_plugins_tencent-1.3.0.tar.gz
| Download URL | livekit_plugins_tencent-1.3.0.tar.gz |
|---|---|
| Size | 9.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e536243249cc894d24a338773b8a1fcacc1119105000a1e8912f2fdcd965601d
|
|
BLAKE2b-256 checksum How to use checksums |
a2975608a2a575fc53d86ee9e4b8cfc5d23ff8d4ddc8c1ef6c5fccc842ed18d9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is 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}
|
Release files / livekit_plugins_tencent-1.3.0-py3-none-any.whl
| Download URL | livekit_plugins_tencent-1.3.0-py3-none-any.whl |
|---|---|
| Size | 8.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4f91a23c0df9cdb6c414f25320a312963f0679b96bf1b3cc997b7ed990dd3386
|
|
BLAKE2b-256 checksum How to use checksums |
4e39874d13ea37ea9374bb875253ff59b56f19f5c481043324a21af8e0d32397
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is 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}
|
Security for livekit-plugins-tencent 1.3.0
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.