The official Java SDK for KugelAudio provides a simple, type-safe interface for text-to-speech generation. Requires Java 17+.
The source is MIT-licensed and on GitHub at
Kugelaudio/java-sdk; issues and pull requests are
welcome there.
Installation
Add the dependency to your pom.xml:
Or with Gradle:
Quick Start
Pre-connecting for Low Latency
By default, new KugelAudio(options) immediately starts a WebSocket connection in the background. This means the connection handshake is absorbed at startup rather than on the first request. See Latency.
Without pre-connecting, the first TTS request includes WebSocket connection setup.
Subsequent requests reuse the connection. See Latency for typical numbers.
The default autoConnect = true moves this overhead to client construction.
Next steps
-
Configuration: client options, authentication modes, regions
-
Generate & Stream: one-shot generation, streaming, word timestamps
-
LLM Sessions: streaming sessions, barge-in, multi-context sessions
-
Voices: list, create, and manage voices
-
Dictionaries: per-project pronunciation and replacement lists
-
Speech to Text: transcribe audio files
-
Types: data models, audio utilities, and a complete example
-
Agent skill: teach your coding assistant to write correct KugelAudio code
Last modified on September 23, 2026