Hardware
| Requirement | Detail |
|---|---|
| Hosts | Linux x86-64 on every machine, CPU-only Kubernetes nodes included. |
| GPU type | NVIDIA. The types, and the GPU count, depend on the model: see Models. Contact Fish Audio before standardizing on a GPU not listed there. |
| GPU count | Two in most deployments: one for the inference worker, one for the vocoder. One more: timestamp alignment, where available. More: adds throughput as more replicas or containers; size it with your account team. |
| MIG | Disable MIG unless the configuration has been validated with Fish Audio. |
| NVIDIA driver | Must support CUDA 13.x and your card’s compute capability. |
Network
| Traffic | Requirement |
|---|---|
| Install | Access to the Fish Audio registry to pull the images and, on Helm, the chart. For a site with no outbound access, see Air-gapped deployments. |
| Billing | With online billing, every request is authorized over HTTPS against the Fish Audio billing endpoint; ask your account team for the hostname to allowlist. Offline billing needs no outbound access. |
| Voice sync | Optional. When turned on, the deployment downloads voices from Fish Audio over HTTPS. |
| Inbound | Your own ingress, load balancer, or private endpoint, with DNS and TLS in place before production traffic. |
Platform-specific requirements
Helm (Kubernetes)
| Requirement | Detail |
|---|---|
| Control plane | 3 CPU-only nodes, roughly 4 vCPU and 16 GB RAM each, for the control plane or, on managed Kubernetes, the system node group. |
| CPU workloads | Roughly 28 vCPU and 125 GiB of memory requests for the non-GPU services, beyond the control plane. Provide a CPU node group, or leave GPU nodes schedulable for them. |
| Shared storage | At least 1 TB of EFS, NFS, or equivalent, mounted at the same path on every node (/mnt/shared by default). The chart mounts it with hostPath and creates no PersistentVolumeClaims. |
| Node-local disk | Redis keeps its data on node-local ephemeral storage. Leave room for it on the nodes that host it, plus headroom for rewrites. |
| Kubernetes | A currently supported minor version and a maintained Helm release. |
| GPU runtime | NVIDIA GPU Operator, or the provider’s driver and device plugin, with GPU nodes exposing nvidia.com/gpu. |
| Pod Security | The namespace must permit hostPath volumes for every service on shared storage, and hostPID and hostIPC for the inference workers. |
The shared mount is created with
DirectoryOrCreate. A node that is missing it
silently gets a local directory instead, and the deployment looks healthy while data
splits across nodes. Verify the mount, and that it is writable, on every node
before installing.All-in-One (Docker)
| Requirement | Detail |
|---|---|
| Docker | Docker Engine 24 or newer, with the NVIDIA Container Toolkit installed and its nvidia runtime registered. |
| CPU and RAM | 32 vCPU and 128 GiB minimum; 48 to 64 vCPU and 192 GiB recommended. |
| Disk | For S2.1 Pro, 100 GB free to pull the image, or 120 GB to load it from a file; Drama 3 needs more. Plus a persistent volume for caches, voices, and the usage ledger; local disk is enough. |