# 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).
# Pin a specific version — vllm/vllm-omni does NOT publish `latest`;
# `:latest` 404s with "manifest unknown". v0.18.0 was released
# 2026-03-29, one day after the Voxtral 4B TTS release, and is the
# first vLLM-Omni cut with Voxtral support.
VOXTRAL_VLLM_TAG=v0.18.0

# 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).
# Was 8197 — moved to 8201 (2026-06-02): 8197 is taken by the live
# chatterbox-fast stack. Don't reuse 8197.
VOXTRAL_PORT=8201
VOXTRAL_BIND=0.0.0.0

# ── runtime / GPU ────────────────────────────────────────────────────
# GPU pinning. "0" = RTX 3090 (24 GB), "1" = RTX A6000 (48 GB).
# Pinned to GPU 0 (3090) — the A6000 is fully booked by Fish S2-Pro
# (~17 GB) + Qwen3-TTS / IndexTTS-2 / VibeVoice slots. Voxtral 4B BF16
# needs ~10-12 GB practical (model + small KV); the 3090's 24 GB is
# enough alongside Kokoro (~1 GB) + Chatterbox (~3 GB) + Kyutai (~6 GB).
VOXTRAL_GPU_DEVICES=0

# vLLM GPU memory utilization fraction (0.0-1.0). On the 3090 alongside
# Kokoro/Chatterbox/Kyutai (~10 GB used), 0.5 = ~12 GB target gives
# Voxtral enough room for weights + KV. Bump to 0.85 if Voxtral ever
# moves to a dedicated GPU.
VOXTRAL_GPU_UTIL=0.5

# ── HuggingFace auth ─────────────────────────────────────────────────
# HF_TOKEN — required to dodge 429 rate limits on Voxtral download.
# HF aggressively throttles unauthenticated IPs that pull large repos.
# Generate one at https://huggingface.co/settings/tokens (a read-only
# token is sufficient). Without this, the first model download fails
# mid-stream and vLLM aborts engine init.
VOXTRAL_HF_TOKEN=

# ── 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