> ## Documentation Index
> Fetch the complete documentation index at: https://hanabiaiinc-docs-enterprise-self-hosting.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction
> Run the Fish Audio Enterprise speech stack inside your own infrastructure
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](/developer-guide/self-hosting/kubernetes) for the
Helm forms and [All-in-One container](/developer-guide/self-hosting/all-in-one)
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. |
```text theme={null}
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
Self-hosting is enabled per team under an enterprise agreement. Reach out
through [fish.audio/enterprise](https://fish.audio/enterprise) with your GPU
target, expected concurrency, and whether you need air-gapped operation.
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.
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](/developer-guide/self-hosting/registry-access).
Connection values are per-team and are only shown in the dashboard. This
documentation uses placeholders such as `` and ``
wherever a value from that page belongs.
## Next steps
GPU, CPU, memory, storage, and platform baselines.
Create a deploy token and authenticate Docker and Helm.
Install, upgrade, roll back, and validate the Helm release.
Run the whole stack from a single `docker run`.
Mirror artifacts, account for usage offline, and prove zero egress.
Monitoring signals, scaling, backups, and troubleshooting.