Skip to main content
Server-side SDKs for the Speech to Text real-time API. They are optional: any language can call the REST and WebSocket API directly. They use the same API key, Characters balance and History as the REST API.
Use the SDKs on your server only. The access key must never reach a browser or mobile app. For a browser client, call createTicket on your server and pass the single-use ticket to the browser. The SDKs themselves always connect with the access key.

​
Install

Install 1.0.0 with the command for your language. Go is served by the Go module proxy (tag go/v1.0.0). Python (wheel and sdist) and Java (JAR, sources, Javadoc and POM) are distributed as files on the GitHub Release v1.0.0, together with release notes and SHA256SUMS. Source code: MyVocal-AI/myvocal-stt-realtime-sdks (Apache License 2.0).
For Java, after installing the files into your local Maven repository, add the dependency:
Set MYVOCAL_ACCESS_KEY in the server environment. The default endpoint is https://api.myvocal.ai.

​
Send your first audio

Each language page starts with a complete example that streams a file and prints the transcript:

Python

Blocking and asyncio clients.

Java

Blocking calls, CompletableFuture and listeners.

Go

context.Context, typed events and errors.

​
Lifecycle, disconnects and errors

The SDK frames audio (about 100 ms per frame), tracks sample cursors, follows in-connection rotation and ends the session when you call finish. The behavior guide covers finish vs close, disconnects, pause and resume, events, errors and observed service behavior. It applies to all three SDKs.