Skip to main content
The real-time SDKs wrap the real-time API for server-side code. You configure a session, hand it audio, consume events and call finish. The SDK frames audio (about 100 ms per frame), tracks sample cursors, follows in-connection rotation and ends the session for you. 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

Source code, release notes and checksums: GitHub Release v1.0.0 of MyVocal-AI/myvocal-stt-realtime-sdks (Apache License 2.0). This page will be updated when the PyPI and Maven Central listings are live. Until then, use the commands below; they install the same 1.0.0 files.
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.

Next steps

Java quickstart

Blocking calls, CompletableFuture and listeners.

Go quickstart

context.Context, typed events and errors.

Python quickstart

Blocking and asyncio clients.
Read the SDK behaviour guide for finish vs close, disconnects, pause and resume, events and errors. It applies to all three SDKs.