# Voxtral TTS stack tunables. Copy to `.env` on irv-ml1 before
# deploying.

# ── image pin ────────────────────────────────────────────────────────
# vLLM-Omni image tag (Mistral's partner serving stack for Voxtral).
# Use a specific version rather than `latest` — vLLM moves fast and
# Voxtral has version-specific compatibility.
VOXTRAL_VLLM_TAG=latest

# Voxtral model on Hugging Face. The 4B variant is the only released
# checkpoint as of 2026-04. Default BF16 weights are ~8 GB.
VOXTRAL_MODEL=mistralai/Voxtral-4B-TTS-2603

# ── network ──────────────────────────────────────────────────────────
# Host port (container listens on 8000 internally).
VOXTRAL_PORT=8197
VOXTRAL_BIND=0.0.0.0

# ── runtime / GPU ────────────────────────────────────────────────────
# GPU pinning. "0" = RTX 3090 (24 GB), "1" = RTX A6000 (48 GB).
# Voxtral 4B BF16 needs ~16 GB practical (model + KV + activation).
# Pinned to A6000 by default for headroom. The 3090 fits but is tight
# for long streaming sessions.
VOXTRAL_GPU_DEVICES=1

# vLLM GPU memory utilization fraction (0.0-1.0). 0.85 = leave 15%
# headroom for other processes / KV cache spikes. Lower if running
# alongside other GPU workloads on the same device.
VOXTRAL_GPU_UTIL=0.85

# ── persistent storage on the host ───────────────────────────────────
# HF cache — first start pulls the Voxtral checkpoint (~8 GB) into
# this dir. Persistent across container recreates.
VOXTRAL_CACHE_DIR=/worktank/voxtral/hf_cache

# Reference voices for cloning. Read-only mount inside the container.
# Drop ~5-15 s WAV / FLAC clips here.
VOXTRAL_VOICES_DIR=/worktank/voxtral/voices