vixy
ed579a77ee
- 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 🦊
21 lines
437 B
Plaintext
21 lines
437 B
Plaintext
# 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
|