TTS_HOME=voices HF_HOME=voices # Worker processes for concurrent TTS requests # Use WORKERS=1 for GPU models like Qwen3-TTS (each worker loads its own model copy) # Use WORKERS=4 for CPU models like Piper WORKERS=1 #PRELOAD_MODEL=xtts #PRELOAD_MODEL=xtts_v2.0.2 #EXTRA_ARGS=--log-level DEBUG --unload-timer 300 #USE_ROCM=1 # Optional HuggingFace token for higher download rate limits. # Not required — F5-TTS / Qwen3-TTS checkpoints are public and downloadable # anonymously. Set in your local speech.env (NOT here — sample.env is committed) # if you hit rate limits during model pull. #HF_TOKEN=