Initial commit: OrpheusTail TTS service

- FastAPI service replacing VoiceTail (Bark)
- Emotion tags: <laugh>, <sigh>, <gasp>, etc.
- Voice cloning endpoint (implementation pending)
- Streaming support for head playback
- Same port 8766 for drop-in replacement

Created by Vixy on Day 71 🦊

requirements.txt

@@ -0,0 +1,20 @@
+# OrpheusTail - Orpheus TTS Service Dependencies
+
+# Web framework
+fastapi>=0.104.0
+uvicorn[standard]>=0.24.0
+
+# Orpheus TTS
+# orpheus-speech is installed separately in Dockerfile
+# It pulls vllm as a dependency
+
+# Audio processing
+scipy>=1.10.0
+numpy>=1.24.0
+
+# Data validation
+pydantic>=2.0.0
+
+# Note: PyTorch should already be installed via JetPack
+# vllm is pulled by orpheus-speech
+# If issues with vllm version, pin to: vllm==0.7.3