# VibeVoice 1.5B (long-form) stack tunables.
# Copy to `.env` on irv-ml1 before deploying.

# ── build pin ────────────────────────────────────────────────────────
# SHA of groxaxo/VibeVoice-FastAPI1 (a more current fork of
# ncoder-ai/VibeVoice-FastAPI). Bump + rebuild when you want upstream
# wrapper updates. Use the FULL 40-char SHA — docker buildx's git
# source resolver doesn't accept short hashes, even when they're
# unambiguous (it errors with "repository does not contain ref X").
VIBEVOICE_SHA=7614c469a145dafc30b1fd5f6a6046ea831dbd6a

# Local image tag — bump when you change build context to force a
# fresh layer build.
VIBEVOICE_TAG=v1

# ── network ──────────────────────────────────────────────────────────
# Host port. Container listens on 8001 internally.
# Reserved on irv-ml1: 8188 ComfyUI, 8190 CosyVoice, 8191 Qwen3-TTS,
# 8192 IndexTTS-2, 8193 Kokoro, 8765 Parakeet. 8194 picked here.
VIBEVOICE_PORT=8194

# Bind address. 0.0.0.0 exposes on all interfaces (incl. WG tunnel
# interface 10.100.79.3); 127.0.0.1 restricts to local-only.
VIBEVOICE_BIND=0.0.0.0

# ── runtime / GPU ────────────────────────────────────────────────────
# Devices visible inside the container. "1" pins to the RTX A6000 —
# 1.5B fits easily on the 3090 too, but pinning to the bigger card
# leaves headroom if you later flip VIBEVOICE_MODEL to the 7B variant.
VIBEVOICE_GPU_DEVICES=1

# Model. Options (per groxaxo/ncoder-ai docs):
#   microsoft/VibeVoice-1.5B        — flagship, ~7 GB bf16 VRAM
#   rsxdalv/VibeVoice-Large         — 7B variant, ~18 GB bf16 VRAM
#                                     (need device_ids="1" / A6000)
#   FabioSarracino/VibeVoice-Large-Q8 — 7B int8 quantized, ~10 GB
VIBEVOICE_MODEL=microsoft/VibeVoice-1.5B

# Number of denoising inference steps. Default 10 is a good
# quality/speed tradeoff. Lower = faster but lower quality.
VIBEVOICE_INFERENCE_STEPS=10

# Compute dtype. bfloat16 default (best speed/quality on Ampere+).
# Use float16 for older GPUs without bf16 support.
VIBEVOICE_DTYPE=bfloat16

# Attention impl. flash_attention_2 is fastest if installed (bundled
# in the upstream image build). Fall back to "sdpa" if it errors.
VIBEVOICE_ATTN=flash_attention_2

# Quantization. Empty = none. "int8_torchao" saves ~40% VRAM at a
# small quality cost — useful if you want to run 7B on a smaller GPU.
VIBEVOICE_QUANT=

# torch.compile. Bumps cold-start by ~3-5 min the first time but
# trims per-generation latency. Disable if you're iterating quickly.
VIBEVOICE_TORCH_COMPILE=false
VIBEVOICE_TORCH_COMPILE_MODE=default

# CFG (classifier-free guidance) scale. Default 1.8 from upstream;
# higher = stronger adherence to text/voice, lower = more free.
VIBEVOICE_CFG_SCALE=1.8

# Max generation length in audio frames. 5400 = ~6 minutes at the
# native rate. Bump for longer podcasts (each frame takes work).
VIBEVOICE_MAX_GEN_LEN=5400

# ── persistent storage on the host ───────────────────────────────────
# Voice library — flat dir of .wav/.mp3/.flac/.m4a files. Mounted
# read-only into the container. Drop a file in, restart container,
# voice is available. (Restart needed because the upstream wrapper
# scans on init, not per-request.)
VIBEVOICE_VOICES_DIR=/worktank/vibevoice/voices

# HuggingFace cache. Holds VibeVoice weights + any aux models pulled.
# Bind-mounted so model state survives container recreate. Excluded
# from restic (regenerable from HF).
VIBEVOICE_CACHE_DIR=/worktank/vibevoice/cache