vox4ai-skill-lib 0.1.0__tar.gz

vox4ai_skill_lib-0.1.0/.gitignore

@@ -0,0 +1,19 @@
+__pycache__/
+*.py[cod]
+*$py.class
+.venv/
+venv/
+ENV/
+.idea/
+.vscode/
+build/
+dist/
+.mypy_cache/
+.ruff_cache/
+.pytest_cache/
+*.log
+.env
+.env.local
+uv.lock
+GEMINI.md
+.coverage

vox4ai_skill_lib-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 vox4ai
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

vox4ai_skill_lib-0.1.0/PKG-INFO

@@ -0,0 +1,139 @@
+Metadata-Version: 2.4
+Name: vox4ai-skill-lib
+Version: 0.1.0
+Summary: TTS skill for AI agents — synthesize, play, save speech via tts-plugin-bridge
+Project-URL: Homepage, https://github.com/vox4ai/vox4ai-skill-lib
+Project-URL: Repository, https://github.com/vox4ai/vox4ai-skill-lib
+Project-URL: Issues, https://github.com/vox4ai/vox4ai-skill-lib/issues
+Author-email: utenadev <utena.cross+pypi@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: agent-skill,ai-agent,speech,synthesis,tts,tts-plugin,voice
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+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 :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: aiohttp
+Requires-Dist: tts-plugin-bridge
+Description-Content-Type: text/markdown
+
+# vox4ai-skill-lib
+
+<p align="center">
+  <img src="https://via.placeholder.com/1200x400/1a1a1a/ffffff?text=vox4ai-skill-lib" alt="vox4ai-skill-lib Banner" width="1200">
+</p>
+
+<p align="center">
+  <img src="https://img.shields.io/badge/pypi-latest-blue.svg" alt="PyPI version">
+  <img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License">
+  <img src="https://img.shields.io/badge/python-3.10%2B-yellow.svg" alt="Python Version">
+  <img src="https://img.shields.io/badge/maintained%3F-yes-brightgreen.svg" alt="Maintained">
+</p>
+
+<p align="center">
+  <a href="https://github.com/vox4ai/vox4ai-skill-lib">Website</a> •
+  <a href="https://github.com/vox4ai/vox4ai-skill-lib/issues">Report Bug</a> •
+  <a href="https://github.com/vox4ai/vox4ai-skill-lib/contributing">Contributing</a>
+</p>
+
+---
+
+## 🚀 Overview
+
+Python ライブラリとしての TTS Skill — AI agent や CLI から `tts-plugin-bridge` の TTS Engine を統一的に操作します。
+
+## 📦 Installation
+
+```bash
+uv add vox4ai-skill-lib
+```
+
+## 🛠 Usage
+
+### 🧩 TTSSkill（推奨）
+
+```python
+import asyncio
+from vox4ai_skill_lib import TTSSkill
+
+async def main():
+    async with TTSSkill(default_engine="edgetts") as skill:
+        # 音声合成（Base64 で音声データ取得）
+        result = await skill.synthesize(text="こんにちは")
+        print(result["status"])  # "ok"
+
+        # ファイル保存
+        result = await skill.save(text="こんにちは")
+
+        # ストリーミング再生（ffplay 優先）
+        result = await skill.say(text="こんにちは")
+
+        # モデル指定
+        result = await skill.synthesize(
+            text="こんにちは",
+            model="ja-JP-KeitaNeural",
+        )
+
+asyncio.run(main())
+```
+
+### ⌨️ API 関数（簡易呼び出し用）
+
+```python
+import asyncio
+from vox4ai_skill_lib.api import list_engines, play_text
+
+async def main():
+    await list_engines()
+    await play_text("こんにちは", engine="edgetts", speed=1.0,
+                    volume=None, pitch=None, style_id=None,
+                    model="ja-JP-NanamiNeural", engine_kwargs={})
+
+asyncio.run(main())
+```
+
+### 📑 TTSSkill API
+
+| メソッド | 説明 |
+|----------|------|
+| `synthesize()` | 音声合成 → Base64 音声データを dict で返す |
+| `save()` | `synthesize()` のエイリアス |
+| `play()` | ストリーミング再生（ffplay）またはファイル再生（paplay/aplay） |
+| `say()` | `play()` のエイリアス |
+| `close()` | 全コネクタをクローズ |
+
+全メソッドで `model` / `pitch` / `volume` / `style_id` / `engine` を **kwargs として受け付けます**。
+
+コンテキストマネージャ対応:
+
+```python
+async with TTSSkill(default_engine="edgetts") as skill:
+    result = await skill.synthesize(text="test")
+# close() 自動呼び出し
+```
+
+### 📑 API 関数
+
+| 関数 | 説明 |
+|------|------|
+| `list_engines()` | 利用可能な TTS Engine 一覧を表示 |
+| `synthesize_text()` | 音声合成 + ファイル保存 / Base64 表示 |
+| `play_text()` | テキスト読み上げ（ストリーミング + ファイルフォールバック） |
+| `test_connection()` | TTS Engine への接続テスト |
+
+## 📦 Dependencies
+
+- `tts-plugin-bridge` — コアフレームワーク（protocol / factory / chunker）
+- `aiohttp` — 非同期 HTTP
+
+## 📜 License
+
+MIT License

vox4ai_skill_lib-0.1.0/README.md

@@ -0,0 +1,112 @@
+# vox4ai-skill-lib
+
+<p align="center">
+  <img src="https://via.placeholder.com/1200x400/1a1a1a/ffffff?text=vox4ai-skill-lib" alt="vox4ai-skill-lib Banner" width="1200">
+</p>
+
+<p align="center">
+  <img src="https://img.shields.io/badge/pypi-latest-blue.svg" alt="PyPI version">
+  <img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License">
+  <img src="https://img.shields.io/badge/python-3.10%2B-yellow.svg" alt="Python Version">
+  <img src="https://img.shields.io/badge/maintained%3F-yes-brightgreen.svg" alt="Maintained">
+</p>
+
+<p align="center">
+  <a href="https://github.com/vox4ai/vox4ai-skill-lib">Website</a> •
+  <a href="https://github.com/vox4ai/vox4ai-skill-lib/issues">Report Bug</a> •
+  <a href="https://github.com/vox4ai/vox4ai-skill-lib/contributing">Contributing</a>
+</p>
+
+---
+
+## 🚀 Overview
+
+Python ライブラリとしての TTS Skill — AI agent や CLI から `tts-plugin-bridge` の TTS Engine を統一的に操作します。
+
+## 📦 Installation
+
+```bash
+uv add vox4ai-skill-lib
+```
+
+## 🛠 Usage
+
+### 🧩 TTSSkill（推奨）
+
+```python
+import asyncio
+from vox4ai_skill_lib import TTSSkill
+
+async def main():
+    async with TTSSkill(default_engine="edgetts") as skill:
+        # 音声合成（Base64 で音声データ取得）
+        result = await skill.synthesize(text="こんにちは")
+        print(result["status"])  # "ok"
+
+        # ファイル保存
+        result = await skill.save(text="こんにちは")
+
+        # ストリーミング再生（ffplay 優先）
+        result = await skill.say(text="こんにちは")
+
+        # モデル指定
+        result = await skill.synthesize(
+            text="こんにちは",
+            model="ja-JP-KeitaNeural",
+        )
+
+asyncio.run(main())
+```
+
+### ⌨️ API 関数（簡易呼び出し用）
+
+```python
+import asyncio
+from vox4ai_skill_lib.api import list_engines, play_text
+
+async def main():
+    await list_engines()
+    await play_text("こんにちは", engine="edgetts", speed=1.0,
+                    volume=None, pitch=None, style_id=None,
+                    model="ja-JP-NanamiNeural", engine_kwargs={})
+
+asyncio.run(main())
+```
+
+### 📑 TTSSkill API
+
+| メソッド | 説明 |
+|----------|------|
+| `synthesize()` | 音声合成 → Base64 音声データを dict で返す |
+| `save()` | `synthesize()` のエイリアス |
+| `play()` | ストリーミング再生（ffplay）またはファイル再生（paplay/aplay） |
+| `say()` | `play()` のエイリアス |
+| `close()` | 全コネクタをクローズ |
+
+全メソッドで `model` / `pitch` / `volume` / `style_id` / `engine` を **kwargs として受け付けます**。
+
+コンテキストマネージャ対応:
+
+```python
+async with TTSSkill(default_engine="edgetts") as skill:
+    result = await skill.synthesize(text="test")
+# close() 自動呼び出し
+```
+
+### 📑 API 関数
+
+| 関数 | 説明 |
+|------|------|
+| `list_engines()` | 利用可能な TTS Engine 一覧を表示 |
+| `synthesize_text()` | 音声合成 + ファイル保存 / Base64 表示 |
+| `play_text()` | テキスト読み上げ（ストリーミング + ファイルフォールバック） |
+| `test_connection()` | TTS Engine への接続テスト |
+
+## 📦 Dependencies
+
+- `tts-plugin-bridge` — コアフレームワーク（protocol / factory / chunker）
+- `aiohttp` — 非同期 HTTP
+
+## 📜 License
+
+MIT License

vox4ai_skill_lib-0.1.0/pyproject.toml

@@ -0,0 +1,57 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "vox4ai-skill-lib"
+version = "0.1.0"
+description = "TTS skill for AI agents — synthesize, play, save speech via tts-plugin-bridge"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "tts-plugin-bridge",
+    "aiohttp",
+]
+license = {text = "MIT"}
+authors = [
+    {name = "utenadev", email = "utena.cross+pypi@gmail.com"},
+]
+keywords = ["tts", "tts-plugin", "voice", "speech", "synthesis", "agent-skill", "ai-agent"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+
+[project.urls]
+Homepage = "https://github.com/vox4ai/vox4ai-skill-lib"
+Repository = "https://github.com/vox4ai/vox4ai-skill-lib"
+Issues = "https://github.com/vox4ai/vox4ai-skill-lib/issues"
+
+[tool.uv.sources]
+tts-plugin-bridge = { path = "../tts-plugin-bridge", editable = true }
+
+[dependency-groups]
+dev = [
+    "pytest-cov>=6.0.0",
+    "pytest>=9.0.3",
+    "pytest-asyncio>=1.3.0",
+    "ruff>=0.15.12",
+    "build>=1.0",
+    "twine>=6.0",
+]
+
+[tool.ruff]
+target-version = "py310"
+
+[tool.pytest.ini_options]
+asyncio_mode = "strict"
+testpaths = ["tests"]

vox4ai_skill_lib-0.1.0/src/vox4ai_skill_lib/__init__.py

@@ -0,0 +1,10 @@
+from .skill import TTSSkill
+from .api import list_engines, synthesize_text, play_text, test_connection
+
+__all__ = [
+    "TTSSkill",
+    "list_engines",
+    "synthesize_text",
+    "play_text",
+    "test_connection",
+]

vox4ai_skill_lib-0.1.0/src/vox4ai_skill_lib/api.py

@@ -0,0 +1,151 @@
+import base64
+
+from tts_plugin_bridge import ConnectorFactory
+from tts_plugin_bridge.protocol import ChunkConfig
+
+from .skill import TTSSkill, _play_audio
+from typing import Optional
+
+
+async def list_engines():
+    try:
+        engines = ConnectorFactory.list_available()
+        if engines:
+            print("利用可能なTTSプラグイン:")
+            for engine in engines:
+                print(f"  - {engine}")
+        else:
+            print("利用可能なTTSプラグインが見つかりません。")
+            print("プラグインをインストールするには: uv add tts-plugin-<エンジン名>")
+    except Exception as e:
+        print(f"エラー: {e}")
+        return 1
+    return 0
+
+
+async def synthesize_text(
+    text: str,
+    engine: Optional[str],
+    speed: float,
+    volume: Optional[float],
+    pitch: Optional[float],
+    style_id: Optional[int],
+    output: Optional[str],
+    engine_kwargs: dict,
+    chunk: bool = False,
+    play: bool = False,
+    chunk_config: Optional[ChunkConfig] = None,
+):
+    try:
+        async with TTSSkill(
+            default_engine=engine or "piperplus", **engine_kwargs
+        ) as skill:
+            kwargs: dict = {}
+            if volume is not None:
+                kwargs["volume"] = volume
+            if pitch is not None:
+                kwargs["pitch"] = pitch
+            if style_id is not None:
+                kwargs["style_id"] = style_id
+            if chunk:
+                kwargs["chunk"] = True
+                kwargs["chunk_config"] = chunk_config
+
+            result = await skill.synthesize(
+                text=text, speed=speed, engine=engine, **kwargs
+            )
+
+            if result.ok:
+                audio_data = base64.b64decode(result.audio_base64 or "")
+                if output:
+                    with open(output, "wb") as f:
+                        f.write(audio_data)
+                    print(f"音声データを {output} に保存しました。")
+                    print(f"エンジン: {result.engine}")
+                    print(f"メッセージ: {result.message}")
+                elif play:
+                    ok = await _play_audio(audio_data)
+                    if not ok:
+                        print(
+                            "エラー: 再生に使えるコマンド (paplay / aplay) が見つかりません。"
+                        )
+                        return 1
+                    print(f"✅ 再生完了 (エンジン: {result.engine})")
+                else:
+                    print(f"エンジン: {result.engine}")
+                    print(f"メッセージ: {result.message}")
+                    if result.audio_base64:
+                        print(f"音声データ (Base64): {result.audio_base64[:100]}...")
+                        if len(result.audio_base64) > 100:
+                            print(f"... (全長: {len(result.audio_base64)} 文字)")
+                    else:
+                        print("音声データ: None")
+            else:
+                print(f"エラー: {result.message}")
+                return 1
+    except Exception as e:
+        print(f"エラー: {e}")
+        return 1
+    return 0
+
+
+async def play_text(
+    text: str,
+    engine: Optional[str],
+    speed: float,
+    volume: Optional[float],
+    pitch: Optional[float],
+    style_id: Optional[int],
+    model: Optional[str],
+    engine_kwargs: dict,
+):
+    try:
+        async with TTSSkill(
+            default_engine=engine or "piperplus", **engine_kwargs
+        ) as skill:
+            kwargs: dict = {}
+            if volume is not None:
+                kwargs["volume"] = volume
+            if pitch is not None:
+                kwargs["pitch"] = pitch
+            if style_id is not None:
+                kwargs["style_id"] = style_id
+            if model is not None:
+                kwargs["model"] = model
+            result = await skill.play(text=text, speed=speed, engine=engine, **kwargs)
+            if result.ok:
+                print(f"✅ {result.message} (エンジン: {result.engine})")
+            else:
+                print(f"エラー: {result.message}")
+                return 1
+    except Exception as e:
+        print(f"エラー: {e}")
+        return 1
+    return 0
+
+
+async def test_connection(
+    engine: Optional[str], style_id: Optional[int], engine_kwargs: dict
+):
+    try:
+        async with TTSSkill(
+            default_engine=engine or "piperplus", **engine_kwargs
+        ) as skill:
+            kwargs: dict = {}
+            if style_id is not None:
+                kwargs["style_id"] = style_id
+            result = await skill.synthesize(
+                text="テスト", speed=1.0, engine=engine, **kwargs
+            )
+
+            if result.ok:
+                print("✅ 接続成功!")
+                print(f"エンジン: {result.engine}")
+                print(f"メッセージ: {result.message}")
+            else:
+                print(f"❌ 接続失敗: {result.message}")
+                return 1
+    except Exception as e:
+        print(f"❌ エラー: {e}")
+        return 1
+    return 0