Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.
68
52%
Does it follow best practices?
Impact
100%
2.12xAverage score across 3 eval scenarios
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./skills/azure-ai-voicelive-java/SKILL.mdThe canonical home for this skill is azure-ai-voicelive-java in sickn33/agentic-awesome-skills
Function calling and Azure voice customization
DefaultAzureCredential used
100%
100%
AzureStandardVoice used
0%
100%
AzureCustomVoice used
0%
100%
AzurePersonalVoice used
0%
100%
PersonalVoiceModels constant
0%
100%
Voice wrapped in BinaryData
0%
100%
VoiceLiveFunctionDefinition created
0%
100%
Function description set
37%
100%
Function parameters set
22%
100%
setTools() on session options
0%
100%
setInstructions() set
0%
100%
Event handling and error resilience
receiveEvents() used
0%
100%
Speech start event handled
42%
100%
Speech stop event handled
42%
100%
Audio delta cast
20%
100%
getDelta() called
70%
100%
Error event cast
20%
100%
getError().getMessage() called
70%
100%
doOnError used
0%
100%
onErrorResume returns Flux.empty()
0%
100%
sendInputAudio with BinaryData
0%
100%
RESPONSE_DONE handled
33%
100%
Session setup and audio configuration
Correct groupId/artifactId
100%
100%
Correct SDK version
100%
100%
Async client used
100%
100%
Correct env var names
100%
100%
Session model name
100%
100%
PCM16 audio formats
100%
100%
Sampling rate 24000
100%
100%
NEAR_FIELD noise reduction
100%
100%
Echo cancellation enabled
100%
100%
Whisper-1 transcription
100%
100%
TEXT and AUDIO modalities
100%
100%
ClientEventSessionUpdate sent
100%
100%
Turn detection configured
100%
100%
Voice via BinaryData
100%
100%
7520423
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.