fastapi
uvicorn
loguru
# Qwen3-TTS - state-of-the-art TTS with voice cloning (Apache 2.0)
# 1.7B params, 10 languages, 97ms latency, 12Hz tokenizer
qwen-tts>=0.0.5
# OHF-Voice fork doesn't have installable Python package yet
# Stick with PyPI piper-tts but use absolute paths in config
# piper-tts>=1.2.0
# 🦝 RACCOON TODO: Create our own PyPI package from OHF-Voice fork
# git+https://github.com/OHF-Voice/piper1-gpl.git@v1.3.0#subdirectory=src/python_run
# coqui-tts[languages]
# Silero TTS - actively maintained, small efficient models
# Note: Silero models are loaded via torch.hub, no package install needed
# Models: ~50-100MB each, CPU-friendly, real-time capable
# omegaconf  # Required by Silero TTS
# Chatterbox - emotion control, 23 languages (Resemble AI)
# Install from git since no PyPI package exists yet
# 🦝 RACCOON NOTE: Disabled due to dependency conflict with Coqui TTS
# gradio 5.44.1 requires typer<1.0 and >=0.12, but spacy 3.6.x requires typer<0.10.0
# TODO: Test Chatterbox in isolated environment or wait for dependency updates
# git+https://github.com/resemble-ai/chatterbox.git
# langdetect
pyyaml
# Kokoro TTS - fast decoder-only architecture
# Lightweight decoder-only TTS, 82M params, 24kHz output
# kokoro>=0.9.2
soundfile  # Required by Qwen3-TTS and Kokoro for audio output
datasets  # HuggingFace datasets for voice corpus downloads
torchcodec  # Audio decoding for HuggingFace datasets
transformers>=4.35.0
# Hugging Face Hub for model downloads
huggingface-hub[cli]
# Creating an environment where deepspeed works is complex, for now it will be disabled by default.
#deepspeed

torch; sys_platform != "darwin"
torchaudio; sys_platform != "darwin"
# for MPS accelerated torch on Mac - doesn't work yet, incomplete support in torch and torchaudio
torch; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
torchaudio; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"

# ROCM (Linux only) - use requirements.amd.txt