# OmniVoice (k2-fsa/OmniVoice) — irv-ml1 stack tunables.
# Copy to .env on the host (/opt/docker/compose/omnivoice/.env). The deploy
# playbook seeds .env from this template on first run only.

# Host port (container always listens on 8001). 8199 is free in the irv-ml1
# audio range (8190-8198 + 8765/919x taken; 8201 reserved for voxtral).
OMNIVOICE_PORT=8199
OMNIVOICE_BIND=0.0.0.0

# GPU: device 0 = RTX 3090 on irv-ml1 (device 1 / A6000 is ComfyUI-exclusive).
# OmniVoice runs in <5 GB; the 3090 had ~18 GB free.
OMNIVOICE_GPU_DEVICES=0

# Image tag + optional upstream pin (empty = latest omnivoice on PyPI).
OMNIVOICE_TAG=latest
OMNIVOICE_VERSION=

# Persistent HF weight cache + reference-voice staging on /worktank.
OMNIVOICE_CACHE_DIR=/worktank/omnivoice/hf_cache
OMNIVOICE_VOICES_DIR=/worktank/omnivoice/voices

# Streaming /tts scheduler prior. High = pack aggressively (OmniVoice is diffusion
# with a ~fixed per-call overhead; low priors over-chunk and starve). 20 is
# validated clean on the 3090. Per-request `rtf_prior` overrides this.
OMNIVOICE_STREAM_RTF_PRIOR=20