agent-voice-input 0.1.0__tar.gz

agent_voice_input-0.1.0/LICENSE

@@ -0,0 +1,191 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 xiaohuaxi
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

agent_voice_input-0.1.0/MANIFEST.in

@@ -0,0 +1,5 @@
+include LICENSE README.md README.zh-CN.md config.example.toml config.example.env
+include bin/agent-voice-input
+recursive-include integrations *
+recursive-include tests *.py
+global-exclude __pycache__ *.py[cod]

agent_voice_input-0.1.0/PKG-INFO

@@ -0,0 +1,118 @@
+Metadata-Version: 2.4
+Name: agent-voice-input
+Version: 0.1.0
+Summary: Two-stage context-aware voice input for CLI coding agents.
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/xiaohuaxi/agent-voice-input
+Project-URL: Repository, https://github.com/xiaohuaxi/agent-voice-input
+Project-URL: Issues, https://github.com/xiaohuaxi/agent-voice-input/issues
+Keywords: voice-input,asr,speech-to-text,cli-agent,codex,claude-code,wsl2
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: User Interfaces
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+[English](README.md) | [简体中文](README.zh-CN.md)
+
+# agent-voice-input
+
+Context-aware voice input for CLI coding agents (such as **Codex**, **Claude Code**, and **Antigravity CLI / `agy`**).
+
+Instead of treating terminal dictation like generic chat input, `agent-voice-input` pairs fast speech recognition with lightweight refinement grounded in your active coding session—fixing homophone identifiers, mixed Chinese–English technical terms, and spoken self-corrections before pasting safely into the terminal.
+
+> **Early Release (`v0.1.0`)**: This project currently provides a foundational setup verified primarily on **Windows Terminal + WSL2 (including Remote Desktop)**. Broader terminal support, deeper `tmux` integration, native macOS terminal polish, and more flexible Stage 2 model choices are actively in progress.
+
+---
+
+## How It Works
+
+1. **Active Session Context**: Locates the foreground agent session (via optional terminal title tags or `/proc` root-session scanning while ignoring background subagents) and extracts recent dialogue plus `git status` filenames as context.
+2. **Stage 1 — Speech Recognition**: Applies a local silence gate (`-50 dBFS`) and RMS loudness normalization (`-20 dBFS`), then transcribes audio via cloud ASR (defaults to Alibaba Bailian `qwen3-asr-flash`; also supports Volcengine Doubao, Gemini, or OpenAI-compatible endpoints).
+3. **Stage 2 — Lightweight Context Refinement**: Cleans up technical terms and explicit spoken self-corrections against the extracted session context. For now, Stage 2 defaults to invoking a lightweight model through local Codex CLI (`codex-luna`), and can also be pointed to an OpenAI-compatible API or turned off (`off`).
+4. **Focus-Safe Paste**: Shows recording/recognition/refinement stages in a non-activating HUD pill on Windows, verifies terminal focus right before pasting (never auto-pressing Enter), and keeps text in the clipboard only if you switched to another window.
+5. **Lightweight Setup**: Currently relies only on the Python 3.10+ standard library plus host `ffmpeg` (and built-in `powershell.exe` on WSL2), requiring no extra Python packages.
+
+---
+
+## Quick Start
+
+### 1. Prerequisites
+
+- **Python** `>= 3.10`
+- **ffmpeg** (`sudo apt install ffmpeg` on Ubuntu/WSL2)
+
+### 2. Install
+
+```bash
+uv tool install agent-voice-input
+# Or with pipx / pip:
+# pipx install agent-voice-input
+```
+
+For local development from source:
+
+```bash
+git clone https://github.com/xiaohuaxi/agent-voice-input.git ~/repos/agent-voice-input
+mkdir -p ~/.local/bin
+ln -s ~/repos/agent-voice-input/bin/agent-voice-input ~/.local/bin/agent-voice-input
+```
+
+### 3. Configure
+
+Create `~/.config/agent-voice-input/agent-voice-input.env` (or export variables in your shell) with at least one Stage 1 ASR key:
+
+```bash
+mkdir -p ~/.config/agent-voice-input && chmod 700 ~/.config/agent-voice-input
+cat > ~/.config/agent-voice-input/agent-voice-input.env <<'EOF'
+ALI_API_KEY="<your-dashscope-api-key>"
+EOF
+chmod 600 ~/.config/agent-voice-input/agent-voice-input.env
+```
+
+Other supported credentials include `DOUBAO_ASR_APP_ID` + `DOUBAO_ASR_API_KEY` (Doubao), `GEMINI_API_KEY`, and `OPENAI_API_KEY`. To customize hotkeys, ASR models, or Stage 2 refinement (such as running without Codex CLI via `refiner.provider = "openai-compatible"` or `"off"`), copy [`config.example.toml`](config.example.toml) to `~/.config/agent-voice-input/config.toml` (also see [`config.example.env`](config.example.env)).
+
+### 4. Verify & Run
+
+```bash
+# Check audio bridge, credentials, and session detection
+agent-voice-input doctor
+
+# Start background daemon (defaults to isolated Right Ctrl tap on WSL2)
+agent-voice-input start
+
+# Other common commands
+agent-voice-input status
+agent-voice-input toggle
+agent-voice-input once --duration 4 --dry-run
+agent-voice-input stop
+```
+
+### Optional: Multi-Window Session Title Hooks
+
+If you run multiple agent windows side by side in the same directory, see [`integrations/`](integrations/README.md) for optional terminal title hooks for Codex, Claude Code, and Antigravity CLI.
+
+---
+
+## Development
+
+```bash
+PYTHONPATH=src python3 -m unittest discover -s tests -v
+```
+
+## Acknowledgments
+
+Early exploration for this project was inspired by [`Einstellung/voice-asr`](https://github.com/Einstellung/voice-asr), particularly around pairing `Qwen3-ASR` with technical terminology context biasing for mixed Chinese–English speech, as well as pre-transcription silence gating and loudness normalization.
+
+## License
+
+[Apache-2.0 License](LICENSE)

agent_voice_input-0.1.0/README.md

@@ -0,0 +1,94 @@
+[English](README.md) | [简体中文](README.zh-CN.md)
+
+# agent-voice-input
+
+Context-aware voice input for CLI coding agents (such as **Codex**, **Claude Code**, and **Antigravity CLI / `agy`**).
+
+Instead of treating terminal dictation like generic chat input, `agent-voice-input` pairs fast speech recognition with lightweight refinement grounded in your active coding session—fixing homophone identifiers, mixed Chinese–English technical terms, and spoken self-corrections before pasting safely into the terminal.
+
+> **Early Release (`v0.1.0`)**: This project currently provides a foundational setup verified primarily on **Windows Terminal + WSL2 (including Remote Desktop)**. Broader terminal support, deeper `tmux` integration, native macOS terminal polish, and more flexible Stage 2 model choices are actively in progress.
+
+---
+
+## How It Works
+
+1. **Active Session Context**: Locates the foreground agent session (via optional terminal title tags or `/proc` root-session scanning while ignoring background subagents) and extracts recent dialogue plus `git status` filenames as context.
+2. **Stage 1 — Speech Recognition**: Applies a local silence gate (`-50 dBFS`) and RMS loudness normalization (`-20 dBFS`), then transcribes audio via cloud ASR (defaults to Alibaba Bailian `qwen3-asr-flash`; also supports Volcengine Doubao, Gemini, or OpenAI-compatible endpoints).
+3. **Stage 2 — Lightweight Context Refinement**: Cleans up technical terms and explicit spoken self-corrections against the extracted session context. For now, Stage 2 defaults to invoking a lightweight model through local Codex CLI (`codex-luna`), and can also be pointed to an OpenAI-compatible API or turned off (`off`).
+4. **Focus-Safe Paste**: Shows recording/recognition/refinement stages in a non-activating HUD pill on Windows, verifies terminal focus right before pasting (never auto-pressing Enter), and keeps text in the clipboard only if you switched to another window.
+5. **Lightweight Setup**: Currently relies only on the Python 3.10+ standard library plus host `ffmpeg` (and built-in `powershell.exe` on WSL2), requiring no extra Python packages.
+
+---
+
+## Quick Start
+
+### 1. Prerequisites
+
+- **Python** `>= 3.10`
+- **ffmpeg** (`sudo apt install ffmpeg` on Ubuntu/WSL2)
+
+### 2. Install
+
+```bash
+uv tool install agent-voice-input
+# Or with pipx / pip:
+# pipx install agent-voice-input
+```
+
+For local development from source:
+
+```bash
+git clone https://github.com/xiaohuaxi/agent-voice-input.git ~/repos/agent-voice-input
+mkdir -p ~/.local/bin
+ln -s ~/repos/agent-voice-input/bin/agent-voice-input ~/.local/bin/agent-voice-input
+```
+
+### 3. Configure
+
+Create `~/.config/agent-voice-input/agent-voice-input.env` (or export variables in your shell) with at least one Stage 1 ASR key:
+
+```bash
+mkdir -p ~/.config/agent-voice-input && chmod 700 ~/.config/agent-voice-input
+cat > ~/.config/agent-voice-input/agent-voice-input.env <<'EOF'
+ALI_API_KEY="<your-dashscope-api-key>"
+EOF
+chmod 600 ~/.config/agent-voice-input/agent-voice-input.env
+```
+
+Other supported credentials include `DOUBAO_ASR_APP_ID` + `DOUBAO_ASR_API_KEY` (Doubao), `GEMINI_API_KEY`, and `OPENAI_API_KEY`. To customize hotkeys, ASR models, or Stage 2 refinement (such as running without Codex CLI via `refiner.provider = "openai-compatible"` or `"off"`), copy [`config.example.toml`](config.example.toml) to `~/.config/agent-voice-input/config.toml` (also see [`config.example.env`](config.example.env)).
+
+### 4. Verify & Run
+
+```bash
+# Check audio bridge, credentials, and session detection
+agent-voice-input doctor
+
+# Start background daemon (defaults to isolated Right Ctrl tap on WSL2)
+agent-voice-input start
+
+# Other common commands
+agent-voice-input status
+agent-voice-input toggle
+agent-voice-input once --duration 4 --dry-run
+agent-voice-input stop
+```
+
+### Optional: Multi-Window Session Title Hooks
+
+If you run multiple agent windows side by side in the same directory, see [`integrations/`](integrations/README.md) for optional terminal title hooks for Codex, Claude Code, and Antigravity CLI.
+
+---
+
+## Development
+
+```bash
+PYTHONPATH=src python3 -m unittest discover -s tests -v
+```
+
+## Acknowledgments
+
+Early exploration for this project was inspired by [`Einstellung/voice-asr`](https://github.com/Einstellung/voice-asr), particularly around pairing `Qwen3-ASR` with technical terminology context biasing for mixed Chinese–English speech, as well as pre-transcription silence gating and loudness normalization.
+
+## License
+
+[Apache-2.0 License](LICENSE)

agent_voice_input-0.1.0/README.zh-CN.md

@@ -0,0 +1,94 @@
+[English](README.md) | [简体中文](README.zh-CN.md)
+
+# agent-voice-input
+
+面向命令行 Coding Agent（如 **Codex**、**Claude Code**、**Antigravity CLI / `agy`**）的语境感知语音输入工具。
+
+不同于缺乏代码上下文的通用语音输入法，`agent-voice-input` 采用「极速语音识别 + 结合当前活跃会话上下文的轻量精修」两阶段设计，在粘贴进终端前自动修准同音代码标识符、中英混说术语与口语中途改口。
+
+> **早期版本说明（`v0.1.0`）**：当前版本刚搭好基础框架并跑通核心特性，目前主要在 **Windows Terminal + WSL2（含远程桌面）** 下完成打磨与日常验证；更多终端支持、`tmux` 深度配合、macOS 常用终端真机完善以及更灵活的二阶段精修模型选择等工作仍在持续推进中。
+
+---
+
+## 核心思路
+
+1. **活跃会话上下文抽取**：自动定位前台终端中的主 Agent 会话（支持可选终端标题标签，或通过 `/proc` 扫描并排除后台 subagent），增量提取近期对话与 `git status` 文件名作为上下文参考。
+2. **一阶段语音识别（ASR）**：先在本地做 `-50 dBFS` 静音门控与 `-20 dBFS` 响度归一化，再调用云端语音识别（默认阿里百炼 `qwen3-asr-flash`，亦支持火山豆包、Gemini 或 OpenAI 兼容接口）。
+3. **二阶段轻量语境精修**：结合抽取出的会话上下文修正同音标识符并理顺口语改口。目前暂时默认通过本地 Codex CLI 调用轻量模型（`codex-luna`）完成整理，也可在配置中切换为 OpenAI 兼容接口或直接关闭（`off`）。
+4. **焦点安全粘贴**：Windows 下通过无焦点抢占的顶部胶囊显示录音、识别、精修阶段；上屏前核对终端焦点，仅粘贴不自动按回车，若中途切到其他窗口则只写入剪贴板。
+5. **依赖精简**：当前仅使用 Python 3.10+ 标准库与宿主机 `ffmpeg`（WSL2 下复用系统自带 `powershell.exe`），无需额外安装第三方 Python 包。
+
+---
+
+## 快速开始
+
+### 1. 前置条件
+
+- **Python** `>= 3.10`
+- **ffmpeg**（Ubuntu / WSL2 执行 `sudo apt install ffmpeg`）
+
+### 2. 安装
+
+```bash
+uv tool install agent-voice-input
+# 或使用 pipx / pip：
+# pipx install agent-voice-input
+```
+
+从源码本地软链开发：
+
+```bash
+git clone https://github.com/xiaohuaxi/agent-voice-input.git ~/repos/agent-voice-input
+mkdir -p ~/.local/bin
+ln -s ~/repos/agent-voice-input/bin/agent-voice-input ~/.local/bin/agent-voice-input
+```
+
+### 3. 配置
+
+在 `~/.config/agent-voice-input/agent-voice-input.env`（或直接通过环境变量）配置至少一项一阶段语音识别凭据即可启动：
+
+```bash
+mkdir -p ~/.config/agent-voice-input && chmod 700 ~/.config/agent-voice-input
+cat > ~/.config/agent-voice-input/agent-voice-input.env <<'EOF'
+ALI_API_KEY="<your-dashscope-api-key>"
+EOF
+chmod 600 ~/.config/agent-voice-input/agent-voice-input.env
+```
+
+除 `ALI_API_KEY`（百炼）外，也支持 `DOUBAO_ASR_APP_ID` + `DOUBAO_ASR_API_KEY`（豆包）、`GEMINI_API_KEY` 或 `OPENAI_API_KEY`（详见 [`config.example.env`](config.example.env)）。如需自定义快捷键、模型或未安装 Codex CLI 时改用 `openai-compatible` / 关闭二阶段精修（`off`），可将 [`config.example.toml`](config.example.toml) 保存为 `~/.config/agent-voice-input/config.toml` 按需修改。
+
+### 4. 自检与运行
+
+```bash
+# 检查音频桥接、凭据与会话识别状态
+agent-voice-input doctor
+
+# 启动后台守护进程（WSL2 下默认点按右 Ctrl 开始/结束录音）
+agent-voice-input start
+
+# 其它常用子命令
+agent-voice-input status
+agent-voice-input toggle
+agent-voice-input once --duration 4 --dry-run
+agent-voice-input stop
+```
+
+### 可选：多窗口会话标题钩子
+
+若常在同一项目目录下并行打开多个 Agent 终端窗口，可按 [`integrations/`](integrations/README.zh-CN.md) 为 Codex、Claude Code 或 Antigravity CLI 接入轻量终端标题标签。
+
+---
+
+## 开发与测试
+
+```bash
+PYTHONPATH=src python3 -m unittest discover -s tests -v
+```
+
+## 致谢
+
+本项目早期探索受到 [`Einstellung/voice-asr`](https://github.com/Einstellung/voice-asr) 的启发，尤其是将 `Qwen3-ASR` 与技术术语上下文偏置结合以改善中英混说识别，以及转写前的静音门控与响度归一化思路，特此致谢。
+
+## License
+
+[Apache-2.0 License](LICENSE)

agent_voice_input-0.1.0/bin/agent-voice-input

@@ -0,0 +1,15 @@
+#!/usr/bin/env python3
+"""Lightweight zero-install CLI wrapper for agent-voice-input."""
+from __future__ import annotations
+
+from pathlib import Path
+import sys
+
+_SRC_DIR = Path(__file__).resolve().parent.parent / "src"
+if _SRC_DIR.is_dir() and str(_SRC_DIR) not in sys.path:
+    sys.path.insert(0, str(_SRC_DIR))
+
+from agent_voice_input.cli import main  # noqa: E402
+
+if __name__ == "__main__":
+    raise SystemExit(main())

agent_voice_input-0.1.0/config.example.env

@@ -0,0 +1,23 @@
+# agent-voice-input credential environment template
+# Default location: ~/.config/agent-voice-input/agent-voice-input.env (chmod 600 recommended)
+# Also falls back to ~/.config/voice-input/voice-input.env or process environment variables
+# Naming rule: suffix style preferred (<VENDOR>_API_KEY); prefix aliases (API_KEY_<VENDOR>) also supported
+
+# 1. Alibaba Cloud Bailian / DashScope (default Stage 1 provider: qwen3-asr-flash)
+ALI_API_KEY="<your-dashscope-api-key>"
+# Supported aliases: API_KEY_ALI / DASHSCOPE_API_KEY
+
+# 2. Volcengine Doubao Speech (optional Stage 1 provider; requires both APP_ID and API_KEY)
+DOUBAO_ASR_APP_ID="<your-volcengine-speech-app-id>"
+DOUBAO_ASR_API_KEY="<your-volcengine-speech-access-token>"
+# Supported aliases: APP_ID_DOUBAO_ASR / API_KEY_DOUBAO_ASR
+
+# 3. Volcengine Ark (used when refiner.provider = "openai-compatible" points to volces.com)
+HUOSHAN_API_KEY="<your-volcengine-ark-api-key>"
+# Supported aliases: API_KEY_HUOSHAN / ARK_API_KEY
+
+# 4. Google Gemini (used when asr.provider = "gemini" for single-hop audio + context transcription)
+GEMINI_API_KEY="<your-gemini-api-key>"
+
+# 5. OpenAI or OpenAI-compatible endpoints (used when asr/refiner uses openai-compatible)
+OPENAI_API_KEY="<your-openai-api-key>"

agent_voice_input-0.1.0/config.example.toml

@@ -0,0 +1,59 @@
+# agent-voice-input example configuration
+# Default location: ~/.config/agent-voice-input/config.toml (also falls back to ~/.config/voice-input/config.toml)
+# Or specify explicitly via --config / AGENT_VOICE_INPUT_CONFIG
+
+[hotkey]
+# Windows global hotkey: RControl (default Right Ctrl, 0xA3) | RAlt | RShift | CapsLock | F1..F24 | 0xNN
+key = "RControl"
+# Trigger mode:
+# - "tap_toggle": isolated tap toggles recording start/stop (chords such as RControl+C pass through untouched)
+# - "ptt": push-to-talk (hold to speak, release to transcribe; pressing another key cancels)
+trigger_mode = "tap_toggle"
+tap_max_ms = 1200
+debounce_ms = 180
+
+[audio]
+# Silence gate & RMS loudness normalization (pure stdlib; blocks accidental empty triggers before hitting cloud APIs)
+floor_dbfs = -50.0
+target_dbfs = -20.0
+max_gain_db = 40.0
+min_duration_sec = 0.3
+min_voiced_sec = 0.1
+# WSL2 capture source: "auto" (defaults to resident win_shim Windows WASAPI 16 kHz capture, avoiding WSLg RDPSource zero-packet deadlocks) | "wasapi" | "winmm" | "pulse"
+wsl_source = "auto"
+# Start/stop audio cue is disabled by default to avoid 1-2s RDP audio wake-up lag; enable locally if desired
+beep = false
+# Tail drain seconds after stopping recording (auto-adapts by platform when unset: 0.65s on WSL2/RDP, 0.20s on macOS)
+# tail_drain_sec = 0.65
+
+[asr]
+# Stage 1 speech-to-text provider: "auto" | "ali" | "doubao" | "gemini" | "openai-compatible"
+provider = "auto"
+# Leave empty to select each provider's default model automatically:
+# - ali -> "qwen3-asr-flash" (also supports "fun-asr-realtime" / "qwen-audio-3.0")
+# - doubao -> "bigmodel"
+# - gemini -> "gemini-2.5-flash" (single-hop audio + context refinement; skips Stage 2 by default)
+# - openai-compatible -> "gpt-4o-transcribe" (or a local faster-whisper-server model name)
+model = ""
+# Doubao resource slot: "auto" (auto-probes and caches available slot) or explicit e.g. "volc.seedasr.auc"
+resource_id = "auto"
+base_url = ""
+api_key_env = ""
+hotwords_file = "~/.config/agent-voice-input/hotwords.txt"
+timeout_sec = 15.0
+
+[refiner]
+# Stage 2 context-aware refinement engine:
+# - "codex-luna" (default: resident codex app-server in-memory thread paired with a lightweight fast model)
+# - "openai-compatible"
+# - "off"
+provider = "codex-luna"
+model = "gpt-6-luna"
+effort = "low"
+# When provider = "openai-compatible", point base_url to Volcengine Ark / OpenAI / a local server:
+# base_url = "https://ark.cn-beijing.volces.com/api/v3"
+base_url = ""
+api_key_env = ""
+max_turns_per_thread = 20
+timeout_sec = 12.0
+force_on_single_hop = false