AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

azure-ai-voicelive-java

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket. Triggers: "VoiceLiveClient java", "voice assistant java", "real-time voice java", "audio streaming java", "voice activity detection java".

Original source
microsoft
License
MIT
Pinned revision
3f5b461b2314e01c400564051e92469114c5b68f

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read microsoft--azure-ai-voicelive-java at revision 3f5b461b2314e01c400564051e92469114c5b68f, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 2

references/examples.md · 24000

-api-key>

For DefaultAzureCredential

AZURE_CLIENT_ID= AZURE_CLIENT_SECRET= AZURE_TENANT_ID=


## Best Practices

1. **Use async client** — VoiceLive requires reactive patterns for real-time streaming
2. **Configure turn detection** — Tune VAD settings for natural conversation flow
3. **Enable noise reduction** — Use `AudioNoiseReduction` for better speech recognition
4. **Handle interruptions** — Set `setInterruptResponse(true)` for natural conversations
5. **Use Whisper transcription** — Enable for input audio transcription
6. **Close sessions properly** — Clean up resources when conversation ends
7. **Buffer audio appropriately** — Send audio in ~100ms chunks for optimal latency
8. **Implement error recovery** — Handle connection drops with reconnection logic