Add /v1/models endpoint for voice discovery

- Implemented GET /v1/models endpoint
- Returns list of all TTS models with metadata
- Includes voice lists for each model
- Provides engine-specific information (sample rate, description)
- Enables frontend voice discovery and model type mapping

Response format:
{
  "object": "list",
  "data": [
    {
      "id": "tts-1",
      "engine": "piper",
      "description": "Fast neural TTS with 100+ voices",
      "sample_rate": 22050,
      "voices": [...],
      "voice_count": 40
    },
    ...
  ]
}

🦝 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

speech.py

@@ -286,6 +286,55 @@ def build_ffmpeg_args(response_format, input_format, sample_rate):
 
     return ffmpeg_args
 
+@app.get("/v1/models")
+async def list_models():
+    """List all available TTS models and their supported voices"""
+    default_exists('config/voice_to_speaker.yaml')
+
+    with open('config/voice_to_speaker.yaml', 'r', encoding='utf8') as file:
+        voice_map = yaml.safe_load(file)
+
+    models_data = []
+
+    for model_id, voices in voice_map.items():
+        if isinstance(voices, dict):
+            voice_list = list(voices.keys())
+
+            # Add model metadata
+            model_info = {
+                "id": model_id,
+                "object": "model",
+                "created": 1700000000,  # Static timestamp
+                "owned_by": "uncloseai",
+                "voices": voice_list,
+                "voice_count": len(voice_list)
+            }
+
+            # Add engine-specific metadata
+            if model_id == 'tts-1':
+                model_info["engine"] = "piper"
+                model_info["description"] = "Fast neural TTS with 100+ voices"
+                model_info["sample_rate"] = 22050
+            elif model_id == 'tts-1-hd':
+                model_info["engine"] = "xtts"
+                model_info["description"] = "High-quality voice cloning TTS"
+                model_info["sample_rate"] = 24000
+            elif model_id == 'tts-1-silero':
+                model_info["engine"] = "silero"
+                model_info["description"] = "Fast multilingual TTS (en, ru, de, es, fr)"
+                model_info["sample_rate"] = 48000
+            elif model_id == 'tts-1-kokoro':
+                model_info["engine"] = "kokoro"
+                model_info["description"] = "Lightweight decoder-only TTS (82M params)"
+                model_info["sample_rate"] = 24000
+
+            models_data.append(model_info)
+
+    return {
+        "object": "list",
+        "data": models_data
+    }
+
 @app.post("/v1/audio/speech", response_class=StreamingResponse)
 async def generate_speech(request: GenerateSpeechRequest):
     global xtts, args