tts-plugin-edgetts 0.1.0__py3-none-any.whl

tts_plugin_edgetts/__init__.py

@@ -0,0 +1,3 @@
+from .connector import EdgeTTSConnector
+
+__all__ = ["EdgeTTSConnector"]

tts_plugin_edgetts/connector.py

@@ -0,0 +1,86 @@
+from typing import AsyncGenerator, Optional
+
+import edge_tts
+from tts_plugin_bridge.protocol import TTSConnector, TTSRequest, TTSResponse
+
+
+class EdgeTTSConnector(TTSConnector):
+    ENGINE_NAME = "edgetts"
+    SUPPORTED_PARAMS = ["voice", "rate", "pitch", "proxy"]
+
+    def __init__(
+        self,
+        voice: str = "ja-JP-NanamiNeural",
+        rate: str = "+0%",
+        pitch: str = "+0Hz",
+        proxy: Optional[str] = None,
+    ):
+        self.voice = voice
+        self.rate = rate
+        self.pitch = pitch
+        self.proxy = proxy
+
+    @staticmethod
+    def _speed_to_rate(speed: float) -> str:
+        percent = round((speed - 1.0) * 100)
+        return f"{percent:+d}%"
+
+    @staticmethod
+    def _volume_to_percent(volume: float) -> str:
+        percent = round((volume - 1.0) * 100)
+        return f"{percent:+d}%"
+
+    def _build_params(self, req: TTSRequest) -> dict:
+        voice = req.extra.get("voice") or req.model or self.voice
+        rate = req.extra.get("rate") or self._speed_to_rate(req.speed)
+        pitch = req.extra.get("pitch") or self.pitch
+        volume = self._volume_to_percent(req.volume) if req.volume else "+0%"
+        proxy = req.extra.get("proxy") or self.proxy
+        return {
+            "voice": voice,
+            "rate": rate,
+            "pitch": pitch,
+            "volume": volume,
+            "proxy": proxy,
+        }
+
+    async def synthesize(self, req: TTSRequest) -> TTSResponse:
+        try:
+            params = self._build_params(req)
+            communicate = edge_tts.Communicate(req.text, **params)
+
+            audio_chunks: list[bytes] = []
+            async for chunk in communicate.stream():
+                if chunk["type"] == "audio":
+                    audio_chunks.append(chunk["data"])
+
+            if not audio_chunks:
+                return TTSResponse.fail("No audio data received from edge-tts")
+
+            audio_data = b"".join(audio_chunks)
+            return TTSResponse.ok(audio_data=audio_data, metadata={"format": "mp3"})
+        except Exception as e:
+            return TTSResponse.fail(f"{type(e).__name__}: {e}")
+
+    async def synthesize_stream(self, req: TTSRequest) -> AsyncGenerator[bytes, None]:
+        params = self._build_params(req)
+        communicate = edge_tts.Communicate(req.text, **params)
+        async for chunk in communicate.stream():
+            if chunk["type"] == "audio":
+                yield chunk["data"]
+
+    async def is_available(self) -> bool:
+        try:
+            await edge_tts.list_voices()
+            return True
+        except Exception:
+            return False
+
+    async def close(self):
+        pass
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        await self.close()

tts_plugin_edgetts-0.1.0.dist-info/METADATA

@@ -0,0 +1,157 @@
+Metadata-Version: 2.4
+Name: tts-plugin-edgetts
+Version: 0.1.0
+Summary: Microsoft Edge TTS 向け TTS Plugin (edge-tts backend)
+Project-URL: Homepage, https://github.com/vox4ai/tts-plugin-edgetts
+Project-URL: Repository, https://github.com/vox4ai/tts-plugin-edgetts
+Project-URL: Issues, https://github.com/vox4ai/tts-plugin-edgetts/issues
+Author-email: utenadev <utena.cross+pypi@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: edge,edgetts,microsoft,speech,synthesis,tts,tts-plugin,voice
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+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: edge-tts>=7.0
+Requires-Dist: tts-plugin-bridge
+Description-Content-Type: text/markdown
+
+# tts-plugin-edgetts
+
+<p align="center">
+  <img src="https://via.placeholder.com/1200x400/1a1a1a/ffffff?text=tts-plugin-edgetts" alt="tts-plugin-edgetts 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/tts-plugin-edgetts">Website</a> •
+  <a href="https://github.com/vox4ai/tts-plugin-edgetts/issues">Report Bug</a> •
+  <a href="https://github.com/vox4ai/tts-plugin-edgetts/contributing">Contributing</a>
+</p>
+
+---
+
+## 🚀 Overview
+
+[edge-tts](https://github.com/rany2/edge-tts) (Microsoft Edge TTS) を `tts-plugin-bridge` で利用するためのプラグインです。
+APIキー不要で多言語対応のTTSが利用できます。
+
+## 📦 インストール
+
+```bash
+uv add tts-plugin-bridge tts-plugin-edgetts
+```
+
+## ⚙️ 前提条件
+
+- インターネット接続 (Microsoft Edge TTSサービスにアクセス)
+- ローカルサーバー不要
+- 再生には [ffplay](https://ffmpeg.org/ffplay.html) または `paplay` / `aplay` がPATHに存在すること
+  - ffplay がある場合: ストリーミング再生（受信しながら即時再生）
+  - ffplay がない場合: 全取得後に paplay / aplay で再生
+
+## 🛠 Usage
+
+### 🧩 Python API
+
+```python
+from tts_plugin_bridge import TTSSkill
+
+async with TTSSkill(default_engine="edgetts") as skill:
+    # save / synthesize — ファイル保存やBase64取得用
+    res = await skill.save(
+        text="こんにちは、エッジティーティーエスのテストです。",
+        speed=1.2,
+        model="ja-JP-KeitaNeural",
+    )
+
+    # say / play — 直接再生（ffplayストリーミング → paplay/aplay）
+    res = await skill.say(
+        text="ストリーミングで即時再生します。",
+        speed=1.0,
+    )
+```
+
+### 🎤 CLI（vox4ai 推奨）
+
+```bash
+# 直接再生（自動ストリーミング）
+vox4ai say "こんにちは" -e edgetts
+
+# 男性声で再生
+vox4ai say "こんにちは" -e edgetts --model ja-JP-KeitaNeural
+
+# ファイル保存（MP3）
+vox4ai save "こんにちは" -e edgetts -o output.mp3
+
+# 環境診断
+vox4ai --doctor
+```
+
+### ⌨️ CLI（tts-plugin-bridge 後方互換）
+
+```bash
+tts-plugin-bridge synthesize "こんにちは" -e edgetts -o output.mp3
+tts-plugin-bridge play "こんにちは" -e edgetts
+tts-plugin-bridge play "こんにちは" -e edgetts --model ja-JP-KeitaNeural
+```
+
+## 🔧 サポートパラメータ
+
+| パラメータ | 型 | 説明 |
+|---|---|---|
+| `speed` | float | 話速 (1.0=標準, >1.0=速い) → edge-tts `rate` に自動変換 |
+| `volume` | float | 音量倍率 → edge-tts `volume` に自動変換 |
+| `model` | str | 音声名 (例: `ja-JP-KeitaNeural`) → edge-tts `voice` にマッピング |
+| `extra.pitch` | str | ピッチ (例: `+5Hz`, `-10Hz`) |
+| `extra.rate` | str | 話速の直接指定 (例: `+50%`, `-20%`)。speed変換より優先 |
+| `extra.volume` | str | 音量の直接指定 (例: `+100%`)。volume変換より優先 |
+| `extra.voice` | str | 音声名の直接指定。modelより優先 |
+| `extra.proxy` | str | プロキシURL |
+
+### 🗣️ 主な音声一覧
+
+| 音声名 | 性別 | 言語 |
+|---|---|---|
+| `ja-JP-NanamiNeural` | 女性 | 日本語 (デフォルト) |
+| `ja-JP-KeitaNeural` | 男性 | 日本語 |
+| `en-US-EmmaMultilingualNeural` | 女性 | 英語 (多言語対応) |
+| `en-US-AndrewNeural` | 男性 | 英語 |
+
+全音声一覧: `uv run edge-tts --list-voices`
+
+### 📁 出力フォーマット
+
+MP3 (24kHz, 48kbps, mono)
+
+## 🔍 検証環境
+
+- **OS**: Windows 11 + WSL2 (Ubuntu)
+- **確認日**: 2026-05-09
+- **依存**: edge-tts v7.2.8, bridge / vox4ai CLI
+- **確認内容**:
+  - `vox4ai say` によるストリーミング再生（ffplay 経由）
+  - `vox4ai save` による MP3 ファイル保存
+  - `vox4ai --doctor` 環境診断
+  - `tts-plugin-bridge` CLI 後方互換維持
+  - 全ユニットテスト 22件 パス
+
+## 📜 ライセンス
+
+MIT License

tts_plugin_edgetts-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+tts_plugin_edgetts/__init__.py,sha256=4OIoBm__Vwd-Y3kudEJwMXAUZJozZrO6PixiUgjwTJY,72
+tts_plugin_edgetts/connector.py,sha256=80xPL-nMltFJ13mwsNRE_W0qqXHoHW5VKN-J4kgTNb4,2778
+tts_plugin_edgetts-0.1.0.dist-info/METADATA,sha256=t8UHPah_MbhADWEFY_aNVJBb1fvDMOBwn1b0s9_BSFQ,5532
+tts_plugin_edgetts-0.1.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+tts_plugin_edgetts-0.1.0.dist-info/entry_points.txt,sha256=_3VdHQZNdyipE_ZRdZYRYXlMWPIqSJtwd7lBIuI6lx0,80
+tts_plugin_edgetts-0.1.0.dist-info/licenses/LICENSE,sha256=RnwZkqBFkeDYZDf3AlIh-qwLMPsJJajhB2YwaRRDWMU,1062
+tts_plugin_edgetts-0.1.0.dist-info/RECORD,,

tts_plugin_edgetts-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.30.1
+Root-Is-Purelib: true
+Tag: py3-none-any

tts_plugin_edgetts-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[tts_bridge.connectors]
+edgetts = tts_plugin_edgetts.connector:EdgeTTSConnector

tts_plugin_edgetts-0.1.0.dist-info/licenses/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.