Add voice management tool bin/voice_tool.py and dynamic voice switching system

2026-08-07 20:16:35 -04:00
parent 87b54ce8f4
commit 351b87beb8
3 changed files with 168 additions and 5 deletions
@@ -0,0 +1,116 @@
+"""Voice Manager for listing and dynamically changing TTS voices at runtime.
+
+Supports both Kokoro TTS voices and macOS System voices, persisting user voice preferences to disk.
+"""
+
+import json
+from pathlib import Path
+from loguru import logger
+
+# Supported Kokoro TTS voices categorized by style
+KOKORO_VOICES = {
+    "af_heart": "American Female - Warm & Natural (Default)",
+    "af_bella": "American Female - Clear & Expressive",
+    "af_sarah": "American Female - Soft & Smooth",
+    "af_nicole": "American Female - Relaxed",
+    "af_sky": "American Female - Bright",
+    "am_michael": "American Male - Friendly & Crisp",
+    "am_adam": "American Male - Natural",
+    "am_fenrir": "American Male - Deep",
+    "am_puck": "American Male - Energetic",
+    "bf_emma": "British Female - Professional",
+    "bf_isabella": "British Female - Smooth",
+    "bm_george": "British Male - Warm",
+    "bm_fable": "British Male - Expressive",
+}
+
+MACOS_VOICES = {
+    "Moira": "Irish Female",
+    "Daniel": "UK Male",
+    "Samantha": "US Female",
+    "Karen": "Australian Female",
+    "Alex": "US Male",
+}
+
+
+class VoiceManager:
+    """Manages active voice settings and dynamic voice switching."""
+
+    def __init__(self, workspace_dir: Path, tts_processor=None):
+        self._workspace_dir = Path(workspace_dir)
+        self._tts_processor = tts_processor
+        self._config_file = self._workspace_dir / "voice_settings.json"
+        self._active_voice = "af_heart"
+        self.load_saved_voice()
+
+    def set_tts_processor(self, tts_processor):
+        self._tts_processor = tts_processor
+        if self._active_voice:
+            self.apply_voice(self._active_voice)
+
+    def load_saved_voice(self) -> str:
+        if self._config_file.exists():
+            try:
+                data = json.loads(self._config_file.read_text())
+                if "voice" in data:
+                    self._active_voice = data["voice"]
+                    logger.info(f"Loaded saved voice preference: {self._active_voice}")
+            except Exception as e:
+                logger.warning(f"Could not load saved voice settings: {e}")
+        return self._active_voice
+
+    def save_voice(self, voice_name: str):
+        try:
+            self._config_file.write_text(json.dumps({"voice": voice_name}, indent=2))
+        except Exception as e:
+            logger.warning(f"Could not save voice setting: {e}")
+
+    def list_voices(self) -> str:
+        kokoro_lines = [f"- {v}: {desc}" for v, desc in KOKORO_VOICES.items()]
+        macos_lines = [f"- {v}: {desc}" for v, desc in MACOS_VOICES.items()]
+        return (
+            "Available Voices:\n\n"
+            "Kokoro Voices:\n" + "\n".join(kokoro_lines) + "\n\n"
+            "macOS System Voices:\n" + "\n".join(macos_lines)
+        )
+
+    def apply_voice(self, voice_name: str) -> tuple[bool, str]:
+        voice_name = voice_name.strip()
+        matched_voice = None
+
+        # Exact match or fuzzy match
+        for v in {**KOKORO_VOICES, **MACOS_VOICES}:
+            if voice_name.lower() == v.lower():
+                matched_voice = v
+                break
+
+        if not matched_voice:
+            # Partial match search
+            for v in {**KOKORO_VOICES, **MACOS_VOICES}:
+                if voice_name.lower() in v.lower():
+                    matched_voice = v
+                    break
+
+        if not matched_voice:
+            available = ", ".join(list(KOKORO_VOICES.keys()) + list(MACOS_VOICES.keys()))
+            return False, f"Voice '{voice_name}' not found. Available voices: {available}"
+
+        self._active_voice = matched_voice
+        self.save_voice(matched_voice)
+
+        if self._tts_processor:
+            try:
+                # Update Kokoro TTS setting if active
+                if hasattr(self._tts_processor, "_settings"):
+                    self._tts_processor._settings.voice = matched_voice
+                    logger.info(f"Dynamic voice updated to: {matched_voice}")
+                    return True, f"Voice changed to {matched_voice}."
+                elif hasattr(self._tts_processor, "set_voice"):
+                    self._tts_processor.set_voice(matched_voice)
+                    logger.info(f"Dynamic voice updated to: {matched_voice}")
+                    return True, f"Voice changed to {matched_voice}."
+            except Exception as e:
+                logger.error(f"Failed to apply voice to TTS processor: {e}")
+                return False, f"Could not change voice: {e}"
+
+        return True, f"Voice set to {matched_voice}."