Skip to main content
Fish Audio Enterprise can be deployed into infrastructure you control: your own cloud account, an on-premise data center, or a network with no internet access at all. Fish Audio delivers each model’s container images and Helm chart through a private registry; you own the cluster, the network boundary, and the data. The self-hosted stack runs the same speech engine as the hosted API, so requests, audio formats, and voice behavior match what you already build against.

Why self-host

Platforms

Each model ships on two platforms. Your agreement decides which models your team gets; Developer → Self Host shows them. The GPUs each model needs are on Models. On either platform, ingress, DNS, TLS, external load balancing, and network allowlists are yours to choose and configure.

Billing

Each deployment you create under Developer → Self Host has its own license and one of three billing modes. To use more than one mode, create a deployment for each. The same chart and image serve all three.

Supported APIs

A self-hosted deployment serves:
  • Text to speech over HTTP and WebSocket streaming.
  • Reference voices. A request that names a voice by reference_id uses that voice’s archive on the deployment. Your team’s fish.audio voices and Fish Audio’s official voices get there by hand, or over HTTPS through the optional voice sync; the hosted voice library is never read at request time.
  • Word and segment timestamps, optional. They need one more GPU; contact Fish Audio to enable them.
Other Fish Audio products are hosted-only unless your agreement says otherwise.

Getting access

1

Agree the deployment scope

Self-hosting is enabled per team under an enterprise agreement. Reach out through fish.audio/enterprise with your GPU target, expected concurrency, and whether you need air-gapped operation.
2

Get your team enabled

Once your agreement is in place, Fish Audio grants your team the models it is entitled to, and the charts and images that go with them.
3

Create a deploy token and a deployment

Sign in to fish.audio, open Developer → Self Host, and create a deploy token for the registry, then a deployment; the deployment’s page takes you through the install. See Registry & license.

Next steps

Models

The models you can self-host, and where their requirements differ.

Requirements

GPU, CPU, memory, storage, and platform baselines.

Registry & license

Create a deploy token and a deployment, and get its license.

Kubernetes deployment

What the Helm install involves and what to arrange first.

All-in-One container

Run the whole stack from a single docker run.

Air-gapped deployments

Mirror artifacts, account for usage offline, and prove zero egress.

Operations

Monitoring signals, scaling, backups, and upgrades.