pi-voice 0.1.0 → 0.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (9) hide show
  1. package/README.md +49 -46
  2. package/out/cli/cli.js +719 -45
  3. package/out/main/index.js +571 -158
  4. package/out/preload/index.cjs +1 -9
  5. package/out/renderer/assets/index-CdX3ylbA.js +209 -0
  6. package/out/renderer/index.html +3 -140
  7. package/package.json +7 -9
  8. package/build/entitlements.mac.plist +0 -14
  9. package/out/renderer/assets/index-dks-nI81.js +0 -162
package/README.md CHANGED
@@ -1,78 +1,81 @@
1
1
  # pi-voice
2
2
 
3
- ## Setup
3
+ Voice interface for the [Pi Coding Agent](https://github.com/badlogic/pi-mono). Hold a key, speak, and pi executes your instructions with voice feedback.
4
+
5
+ ## Installation
4
6
 
5
7
  ```bash
6
- bun install
7
- bun run build
8
- bun link # `pi-voice` コマンドをグローバルに登録
8
+ npm i -g pi-voice
9
+ # or
10
+ bun i -g pi-voice
9
11
  ```
10
12
 
11
- ## CLI
12
-
13
- pi-voice は **daemon 型**のアプリケーションです。Docker と同じように、`start` でバックグラウンドに常駐し、CLI で操作します。起動時にウィンドウは表示されません。
13
+ ## Usage
14
14
 
15
- `status` / `stop` / `show` は Electron を起動せず、Unix socket 経由で daemon と通信して即応します。
15
+ pi-voice is a daemon-style application that runs in the background once started. You can push-to-talk with the agent.
16
16
 
17
17
  ```bash
18
- # daemon をバックグラウンドで起動（ウィンドウは表示されない）
19
- pi-voice start
18
+ pi-voice start # start the daemon in the background
19
+ pi-voice status # show state, PID, and uptime
20
+ pi-voice stop # stop the daemon
21
+ ```
20
22
 
21
- # daemon の状態を確認（state・PID・uptime を表示）
22
- pi-voice status
23
+ The push-to-talk trigger defaults to `Cmd+Shift+I` (macOS) / `Win+Shift+I` (Windows). Hold the key to record, release to send.
23
24
 
24
- # ウィンドウを表示
25
- pi-voice show
25
+ ## Setting
26
26
 
27
- # daemon を停止（Fn キーも無効化）
28
- pi-voice stop
29
- ```
27
+ ### pi agent configuration
30
28
 
31
- - `start` は引数なしのデフォルトコマンドです。既に起動中ならエラーで終了します。
32
- - `start` は事前に `bun run build` が必要です（`out/main/index.js` がなければエラー）。
33
- - ウィンドウを閉じても daemon はバックグラウンドで動作し続けます。完全に停止するには `stop` か Cmd+Q を使ってください。
34
- - 実行状態は `~/.pi-voice/runtime-state.json`、制御 socket は `~/.pi-voice/daemon.sock` に配置されます。
29
+ pi-voice launches a Pi agent session with the directory where `pi-voice start` was executed. This means **all standard pi configuration works as-is**:
35
30
 
36
- ### 開発モード
31
+ - `AGENTS.md` — walked up from `cwd` to the filesystem root
32
+ - `.pi/settings.json` — project-level settings
33
+ - `.pi/skills/`, `.pi/extensions/`, `.pi/prompts/` — project-level resources
34
+ - `~/.pi/agent/` — global settings, skills, extensions, prompts, and models
35
+ - and more
37
36
 
38
- ```bash
39
- bun run dev:electron
40
- ```
37
+ Refer to the [Pi documentation](https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent) for details on these settings.
41
38
 
42
- HMR 付きの Vite dev server で renderer を配信しつつ Electron を起動します（開発時はウィンドウを閉じると終了します）。
39
+ ### pi-voice configuration
43
40
 
44
- CLI 単体で実行する場合:
41
+ You can configure pi-voice in `.pi/pi-voice.json`:
45
42
 
46
- ```bash
47
- bun run dev:cli
43
+ ```json
44
+ {
45
+ "key": "ctrl+t",
46
+ "provider": "local"
47
+ }
48
48
  ```
49
49
 
50
- ## Build
50
+ | Key | Description |
51
+ | --- | --- |
52
+ | `key` | Push-to-talk shortcut. Combine modifiers (`ctrl`, `shift`, `alt`/`opt`, `meta`/`cmd`) and a main key with `+`. Examples: `"ctrl+t"`, `"alt+space"`, `"ctrl+shift+r"`. Default: `"meta+shift+i"`. |
53
+ | `provider` | Speech provider for STT & TTS. `"local"`, `"gemini"` (Vertex AI), or `"openai"`. Default: `"local"`. |
51
54
 
52
- ```bash
53
- bun run build
54
- ```
55
-
56
- `out/` にプロダクションビルドを出力します。
55
+ ### Environment variables
57
56
 
58
- ## Preview
57
+ | Provider | Required variables |
58
+ | --- | --- |
59
+ | `local` | None (model is auto-downloaded on first launch). Optional: `WHISPER_MODEL_PATH` (custom model path), `WHISPER_MODEL` (model name, default `medium-q5_0`), `SAY_VOICE` (macOS `say` voice name, e.g. `"Kyoko"`). |
60
+ | `gemini` | `GOOGLE_CLOUD_PROJECT`, `GOOGLE_CLOUD_LOCATION` (optional, default `us-central1`) |
61
+ | `openai` | `OPENAI_API_KEY` |
59
62
 
60
- ```bash
61
- bun run preview
62
- ```
63
+ #### Whisper model (local provider)
63
64
 
64
- ビルド済みの成果物で Electron を起動して動作確認します。
65
+ The `local` provider uses [Whisper](https://github.com/openai/whisper) for STT and the macOS `say` command for TTS. On first launch, a ggml-format Whisper model (`medium-q5_0`, ~514 MB) is automatically downloaded to `~/.pi-agent/whisper/` and cached for subsequent runs.
65
66
 
66
- ## Distribution
67
+ To use a different model, set `WHISPER_MODEL`:
67
68
 
68
69
  ```bash
69
- bun run dist
70
+ export WHISPER_MODEL=base # smaller & faster
70
71
  ```
71
72
 
72
- `bun run build` + electron-builder で macOS 向けの dmg/zip を `release/` に生成します。
73
-
74
- パッケージングせずディレクトリ出力のみ（テスト用）:
73
+ Or point to your own model file directly:
75
74
 
76
75
  ```bash
77
- bun run dist:dir
76
+ export WHISPER_MODEL_PATH=/path/to/ggml-custom.bin
78
77
  ```
78
+
79
+ ## Contributing
80
+
81
+ See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, build commands, and release workflow.