Skip to content
← All services

AI

Managed Speech to text on your own cluster

Transcription, translation and text-to-speech behind the OpenAI audio API, on your own hardware.

Created inside a project, beside the apps that use it. Each project gets its own instance, storage and credentials.

A recent addition. It installs today, and the console marks it as new until it has run on a customer's cluster.

01What it does

Speech to text, run for you

Speaches on Anyport's own chart, with Whisper models from Hugging Face kept on a volume.

Transcribe and translate audio with Whisper, and turn text into speech, with the OpenAI SDK pointed at a base URL your apps are bound to. Name a faster-whisper model and it is downloaded before the service starts, so the first request does not wait for it; text-to-speech models are added through the API.

Runs on CPU by default; memory decides which models fit and cores decide how fast audio is transcribed. Switch on the GPU option and it runs the CUDA build on a node with an NVIDIA GPU. Every request asks for the generated API key, so the service can be published on a domain.

02Options

What you choose

What the console asks when you create it, in the catalog's own numbers. Anything marked chosen once cannot change without creating a new instance.

Sizes
small 3Gi, medium 6Gi, large 12Gi of memory
Storage
10Gi by default for model files, chosen once
Model
Any faster-whisper model by name; faster-whisper-small by default
GPU
Optional; needs the NVIDIA device plugin on the cluster
Pause
Yes; the models stay on the volume

03Binding

What your app receives

Bind it to an app and these arrive as environment variables. The values are generated once into a secret and reach the app from there, rather than as something you copy.

  • SPEACHES_HOST
  • SPEACHES_PORT
  • SPEACHES_URL
  • SPEACHES_API_KEY
  • SPEACHES_MODEL

04Adding it

Add Speech to text to a project

The same four steps as every service in the catalog.

  1. 01Open a project and go to Services.
  2. 02Pick it from the catalog and choose its options. Only the size is required; everything else has a default.
  3. 03Create it. Anyport installs it into the project's namespace, generates its credentials into a secret there, and tracks its health.
  4. 04Bind it to an app. The connection details arrive as environment variables, and rotating the credential never means editing an app.
Open the console →How services work →

Also under AI