# CosyVoice stack tunables. Copy to `.env` on irv-ml1 before deploying. # # cp .env.example .env # # edit as needed # docker compose up -d # Image tag. `v1.3.2` (2026-01-18) is the latest wrapper and ships # Fun-CosyVoice3-0.5B-2512 (CosyVoice 3 model). The older `v3.x` # tag family (2025-12-18) also ships CosyVoice 3 — the wrapper # version numbering diverged from the model version, which is # confusing but deliberate upstream. Stay on v1.3.x. # # See https://hub.docker.com/r/neosun/cosyvoice/tags for updates. COSYVOICE_VERSION=v1.3.2 # Host port for the web UI + REST API (container listens on 8188). # Avoiding 8188 on the host since ComfyUI already has it. COSYVOICE_PORT=8190 # Bind address. 0.0.0.0 exposes on all interfaces including the WG # tunnel IP (10.100.79.3). Use 127.0.0.1 to restrict to local-only. COSYVOICE_BIND=0.0.0.0 # Path inside the container for the active model. The image places # Fun-CosyVoice3-0.5B at pretrained_models/Fun-CosyVoice3-0.5B on # first run — keep this default unless upstream ships alternate # model variants. COSYVOICE_MODEL_DIR=pretrained_models/Fun-CosyVoice3-0.5B # Seconds of idleness before the server releases GPU VRAM. Reloading # takes a few seconds; trade off fast re-use vs sharing GPUs with # other workloads (llama-swap style). Default 600 (10 min). COSYVOICE_GPU_IDLE_TIMEOUT=600 # Host paths for persistent data. Must exist and be writable by the # container before first `up`. # voices/ cloned speaker profiles — precious, restic-covered # input/ uploaded source audio — scratch # output/ synthesized clips — scratch, regenerable COSYVOICE_VOICES_DIR=/worktank/cosyvoice/voices COSYVOICE_INPUT_DIR=/worktank/cosyvoice/input COSYVOICE_OUTPUT_DIR=/worktank/cosyvoice/output