Docs/AngeVoice

Choose an AngeVoice deployment

Choose the most stable profile for the hardware. Do not use Legacy GPU only because the host has a GPU.

CPUNVIDIA GPULegacy GPU

Deployment comparison

ProfileBest forAdvantagesWatch for
CPUNAS systems, hosts without NVIDIA GPUs, initial validationBroad compatibility and simpler troubleshootingCloning models may be slower
Standard GPURegular NVIDIA x86_64 hostsKokoro, MOSS and ZipVoice can prefer CUDAThe host driver and container GPU runtime must work
Legacy GPUOlder driver stacks where the standard image cannot startMore conservative compatibility stackNot a performance upgrade; some models use CPU by default

Start manually

# CPU, port 8100
cd docker/cpu && docker compose up -d

# Standard NVIDIA GPU, port 8101
cd docker/gpu && docker compose up -d

# Compatibility profile, port 8102
cd docker/legacy-gpu && docker compose up -d

Confirm that the GPU is actually used

nvidia-smi
curl http://127.0.0.1:8101/v1/models/current
docker logs --tail 200 angevoice-gpu

The status response reports the requested provider, actual provider and fallback reason. requested=cuda with actual=cpu usually means the service is usable but that model fell back to CPU.

Persistent data

models/       Model files and download cache
prompts/      Voice Profiles and reference audio
outputs/      Generated audio
credentials/  Administrator hashes and API key
config/       Runtime configuration
logs/         Logs and diagnostic bundles

Mount the same directories when switching between CPU, GPU and Legacy GPU.

When to switch profiles

SituationRecommendation
The standard GPU image starts and synthesizes correctlyKeep the standard GPU profile
CUDA or cuDNN prevents the standard image from startingUpdate the image and driver first; try Legacy GPU only if the issue remains
GPU memory is insufficientLoad one model at a time or let cloning models fall back to CPU
You only need to validate the APIStart with CPU, then migrate after the full path works