ChatVoice
ChatVoice 是 ChatArch 的录音转写与会议工作区 Python 包，包含 Speakr 网页界面：从语音获得文字，整理摘要，再把值得推进的想法转成可编辑的 Markdown Todo。
按场景开始
| 你要做什么 | 阅读入口 |
|---|---|
| 安装并打开网页 | 快速上手 |
| 录音、整理摘要和继续完善纪要 | 网页使用 |
| 将摘要转为待办，继续对话修改并导出 | Markdown Todo |
| 配置 ASR、文本模型、语音合成或声音复刻 | 配置参考 |
| 部署服务、邀请账号、备份数据 | 部署与启动 |
| 查看命令或接入自己的程序 | CLI 树 · HTTP 接口 · Python 接口树 |
安装与检查
要求 Python 3.10 或更高版本，建议安装到独立虚拟环境。
python -m pip install "ChatVoice[web]==0.2.0"
chatvoice --version
chatvoice --tree
chatvoice serve app --dry-run --json
安装包本身不会自动启动服务，也不会自动下载 GPU 模型。快速上手区分无模型界面体验与真实转写部署。
当前能力
- 会议记录：实时转写、暂停与继续、会议标题、标签、历史记录和复制文字。
- 摘要与纪要：生成摘要，手动编辑纪要，或通过对话修改并撤销。
- Markdown Todo：由用户点击“转为 Todo”，在独立页面继续编辑、对话完善、复制或下载
.md；不会自动转换或执行任务。 - 声音工作室：配置系统音色与输出格式；通过独立声音复刻服务，以授权参考音频生成临时试听结果。
- 实时对话：对接当前支持的 Qwen 实时语音模型，需服务端配置和有效使用权限。
- 程序化访问：命令行、Python 客户端、受限 API Token，以及单文件数据库备份与恢复。
模型配置保留在服务端。摘要和标题使用独立文本设置；Todo 复用摘要模型，不增加一套密钥。ASR HTTP 服务使用 CHATVOICE_ASR_API_URL，本地 FunASR 则需要另行准备模型依赖。
数据与安全边界
账号记录保存到 ~/.chatarch/chatvoice 下的 SQLite；访客记录仅存于当前浏览器。录音会为识别而短暂经过浏览器和服务端，但不作为会议音频档案保存。密钥不进入浏览器。
自助注册关闭，由部署者创建受邀账号。ChatVoice 直接依赖 ChatLogin 0.1.2 的内建 ChatVoiceAuth，复用既有账号、会话和 CSRF；/login 使用可定制的共享 LoginUI。会议所有权和 Token 权限仍由 ChatVoice 控制，访客草稿等待 IndexedDB 事务提交后才跳转登录。详见数据保留边界。
开发
python -m pip install -e ".[web,dev,docs]"
python -m pytest tests -q
mkdocs build --strict
前端控制器回归要求 Node.js 22 或更高版本。普通测试不代表真实模型已经可用；真实服务验收单独执行，见开发与验证。
1 maintainer
Metadata
1 maintainer
Release files for ChatVoice 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| chatvoice-0.2.0.tar.gz | 267.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| chatvoice-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 394.8 kB
Release files / chatvoice-0.2.0.tar.gz
| Download URL | chatvoice-0.2.0.tar.gz |
|---|---|
| Size | 267.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
710f5fcca781232dffe0f31c37b232bbdfecb86078345112f21558e5f11c8aac
|
|
BLAKE2b-256 checksum How to use checksums |
c47743c41159bdbe8963da8cef88ecf26c18da8f6681022d5b721ecd07bfe4f1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency logRelease files / chatvoice-0.2.0-py3-none-any.whl
| Download URL | chatvoice-0.2.0-py3-none-any.whl |
|---|---|
| Size | 127.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
acd8e9b082961a4141408d8c094756688fe7d2dbc93d326e95db6b265b8064a6
|
|
BLAKE2b-256 checksum How to use checksums |
a32d8c32e783cc0bcfa345d67c9de297a3291aae8967006808dc8a1eb0f58ed0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency log
