Introduction

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 container images and a 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

Reason	What it gives you
Colocation	Run inference in the same region, VPC, or rack as your application and remove public-internet round trips from time-to-first-audio.
Single-tenant isolation	Dedicated GPUs and queues. Capacity is not shared with other tenants, and you decide when the deployment is upgraded.
Security posture	Voice traffic never leaves your network. The offline delivery forms make no outbound calls at runtime and run on disconnected networks.
Data sovereignty	Input text, generated audio, and reference voices stay inside your boundary and under your own retention policy.

Delivery forms

The same engine ships in three forms. Your enterprise agreement determines which ones your team is granted.

	Online Helm	Offline Helm	Offline All-in-One
Platform	Kubernetes	Kubernetes	A single container, `docker run`
Model assets	Pulled from an S3-compatible endpoint at startup	Served in-cluster from a bundled model warehouse	Baked into the image
Usage accounting	Validated and billed against the Fish Audio service	Local signed usage ledger	Local signed usage ledger
Runtime egress	Model endpoint and billing endpoint	None	None
Air-gap capable	No	Yes, after mirroring images and charts	Yes
Scaling	Scales replicas across all GPUs and nodes	Scales replicas across all GPUs and nodes	Single node, single inference worker
Best for	Managed clusters with outbound access	Isolated or regulated production clusters	Evaluation, single-node appliances, strict air gaps

Both Helm forms share one deployment procedure and differ only in a few values. See Kubernetes deployment for the Helm forms and All-in-One container for the single-container form.

What is included

Capability	Online Helm	Offline Helm	All-in-One
Text to speech over `POST /v1/tts`	Included	Included	Included
WebSocket streaming	Included	Included	Included
Reference-voice requests (`reference_id`)	From pre-staged archives	From pre-staged archives	From pre-staged archives
Word and segment timestamps	Optional, needs an extra GPU	Not included	Not included
Horizontal scaling and autoscaling	Included	Included	Not included
Prometheus metrics	Included	Included	Container logs only

Timestamp alignment is served by a separate forced-aligner component. It is disabled by default, is not part of the offline model bundle, and is not built into the All-in-One image, so /v1/tts/stream/with-timestamp returns audio without alignment data on those forms. Contact Fish Audio if your deployment needs timestamps.

Reference voices are resolved from archives you stage yourself. A self-hosted deployment does not read from the hosted voice library, and voice models created on fish.audio are not automatically available to it. Products other than text to speech are hosted-only unless your agreement says otherwise.

Architecture at a glance

Component	Role
`edge-api-production`	Entry point. Validates requests, applies product logic, and routes work to the model services.
`oxidengine`	Model API layer that coordinates normalization, inference, and audio decoding.
`sglang-router` and `sglang`	Routing and GPU-backed inference workers.
`vocoder`	GPU-backed audio decoding.
`text-normalizer`	Text normalization ahead of inference.
Redis	Runtime state and cache. Installed by the chart into the release namespace.
Shared storage	Model cache, reference archives, and the usage ledger. Mounted on every node.

client -> your ingress or load balancer -> edge-api -> oxidengine -> sglang-router -> sglang (GPU)
                                                                  -> vocoder (GPU)
                                                                  -> text-normalizer

Fish Audio delivers the deployment at the Kubernetes service level. Ingress, DNS, TLS, external load balancing, and network allowlists are yours to choose and configure.

Getting access

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.

Get your team enabled

Once your agreement is in place, Fish Audio grants your team the artifacts it is entitled to: the Helm chart, the component images, and the All-in-One image where applicable.

Collect your connection values

Sign in to fish.audio and open Developer → Self Host. That page shows the registry host, your login username, the Helm chart base, your team ID, and the exact artifacts your team can pull. Create a deploy token there to authenticate. See Registry access.

Connection values are per-team and are only shown in the dashboard. This documentation uses placeholders such as <registry-host> and <deploy-token> wherever a value from that page belongs.

Next steps

Requirements

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

Registry access

Create a deploy token and authenticate Docker and Helm.

Kubernetes deployment

Install, upgrade, roll back, and validate the Helm release.

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 troubleshooting.

Set Up the SDK

Cookbook

Best Practices

Integrations

Self-Hosting

More

Why self-host

Delivery forms

What is included

Architecture at a glance

Getting access

Next steps

Requirements

Registry access

Kubernetes deployment

All-in-One container

Air-gapped deployments

Operations

​Why self-host

​Delivery forms

​What is included

​Architecture at a glance

​Getting access

​Next steps

Requirements

Registry access

Kubernetes deployment

All-in-One container

Air-gapped deployments

Operations

Why self-host

Delivery forms

What is included

Architecture at a glance

Getting access

Next steps