# Qwen3-TTS stack tunables. Copy to `.env` on irv-ml1 before deploying.

# ── build pin ────────────────────────────────────────────────────────
# SHA of groxaxo/Qwen3-TTS-Openai-Fastapi to build from. Bump + rebuild
# when you want upstream wrapper updates.
QWEN3_TTS_SHA=10323ce778c48a75dbda93d0a4891983fb371f58

# Local image tag — bump when you change build context to force a
# fresh layer build. v2 = first GPU build (target=production); v1
# was the accidental CPU-only image (last stage of upstream's
# multi-stage Dockerfile).
QWEN3_TTS_TAG=v2

# ── network ──────────────────────────────────────────────────────────
# Host port (container listens on 8880 internally).
QWEN3_TTS_PORT=8191

# 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.
QWEN3_TTS_BIND=0.0.0.0

# ── runtime ──────────────────────────────────────────────────────────
# Inference backend. Five options exposed by /app/api/backends/factory.py:
#   official   — default. Naive HF transformers autoregressive loop.
#                Reliable, but the GPU sits at ~27% utilization and
#                TTFB on a sentence is 8-12s (no streaming endpoint
#                tuning). 2026-04-27 bench confirmed.
#   optimized  — torch.compile + CUDA graphs + real-time streaming.
#                Should be the path to upstream's claimed 97 ms TTFB.
#                CRASHES the container during its hardcoded warmup as
#                of 2026-04-27 (silent ExitCode 0, no Traceback, repeats
#                every ~22s under restart policy). TTS_WARMUP_ON_START=
#                false doesn't help — the optimized backend's warmup is
#                separate from the factory-level warmup. Don't use until
#                upstream root-cause is identified or worked around.
#   vllm_omni  — vLLM-Omni-backed. Faster but needs more VRAM and a
#                vLLM dependency we haven't pulled. Untested.
#   pytorch    — CPU-only fallback.
#   openvino   — Intel CPU experimental.
QWEN3_TTS_BACKEND=official

# Model variant. Upstream publishes four checkpoints on HF:
#   Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice — flagship, supports voice cloning + preset voices  (RECOMMENDED)
#   Qwen/Qwen3-TTS-12Hz-1.7B-Base        — flagship, foundation only — REJECTS all synthesis through this wrapper
#   Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice — lightweight cloning-capable variant
#   Qwen/Qwen3-TTS-12Hz-0.6B-Base        — lightweight foundation only
# 1.7B = ~6–8 GB VRAM bfloat16, best quality. 0.6B = ~2–3 GB.
#
# IMPORTANT: the wrapper's only synthesis code path goes through the
# voice cloning machinery. The -Base variants do NOT expose
# generate_custom_voice; they error with "does not support
# generate_custom_voice" on every request, no matter what voice you
# specify (built-ins like Ryan, Vivian etc. count as custom voices).
# Use -CustomVoice. The Base variant is foundation-model territory
# that needs a different harness to be useful.
# (This file had the labels backwards through 2026-04-27 — fixed
# after the 2026-04-27 voice-fleet bench surfaced the failure mode.)
QWEN3_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

# Warm the model on container start so the first synthesis request
# doesn't pay the load latency. Adds ~30 s to startup. Recommended.
QWEN3_TTS_WARMUP=true

# Concurrency cap on synthesis requests. Single GPU + 1.7B model →
# leave at 1 unless you're load-testing.
QWEN3_TTS_MAX_CONCURRENT=1

# Mount the gradio voice-studio UI at /voice-studio for browser-side
# voice cloning. Set "false" to disable for headless deployments.
QWEN3_TTS_VOICE_STUDIO=true

# ── persistent storage on the host ───────────────────────────────────
# HuggingFace cache (model weights, ~5 GB after first run). Bind-mounted
# so model state survives container recreate. Excluded from restic
# (regenerable from HF Hub).
QWEN3_TTS_CACHE_DIR=/worktank/qwen3-tts/cache

# Cloned voice profiles (meta.json + reference.wav per voice). Precious
# — cloned voices need the original reference audio to recreate.
# Included in restic.
QWEN3_TTS_VOICES_DIR=/worktank/qwen3-tts/voices