azure-ai-voicelive-dotnet
Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-voicelive-dotnet74
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 98%
↑ 2.88xAgent success when using this skill
Validation for skill structure
Evaluation results
95%
60%Voice Assistant Prototype for Customer Support
Session configuration and authentication
VoiceLive package
100%
100%
Azure.Identity package
100%
100%
NAudio package
0%
0%
DefaultAzureCredential used
100%
100%
Supported model
100%
100%
Both modalities set
0%
100%
Modalities cleared first
0%
100%
AzureSemanticVadTurnDetection
0%
100%
SilenceDuration 500ms
0%
100%
PrefixPadding 300ms
0%
100%
PCM16 input format
0%
100%
PCM16 output format
0%
100%
AzureStandardVoice class
0%
100%
using statement for session
100%
100%
Without context: $0.4284 · 5m 26s · 26 turns · 96 in / 6,673 out tokens
With context: $0.4637 · 3m 59s · 24 turns · 28 in / 5,656 out tokens
100%
74%Resilient Voice Session Event Processor
Event loop and error handling
GetUpdatesAsync loop
0%
100%
AudioDelta handling
12%
100%
TextDelta handling
12%
100%
ResponseDone handling
12%
100%
Error event handling
12%
100%
Benign error ignored
0%
100%
UserMessageItem used
20%
100%
StartResponseAsync called
100%
100%
Both modalities set
0%
100%
DefaultAzureCredential used
0%
100%
using statement for session
100%
100%
Supported model
100%
100%
Without context: $0.4525 · 4m 3s · 19 turns · 74 in / 8,612 out tokens
With context: $0.9146 · 7m 5s · 31 turns · 461 in / 14,273 out tokens
100%
57%Voice Assistant with Live Data Lookup
Function calling integration
VoiceLiveFunctionDefinition used
0%
100%
BinaryData.FromString for parameters
100%
100%
Tools added to sessionOptions
100%
100%
FunctionCallArgumentsDone event handled
0%
100%
CallId used for response
100%
100%
FunctionCallOutputItem used
33%
100%
StartResponseAsync after function result
100%
100%
GetUpdatesAsync loop
37%
100%
Both modalities set
0%
100%
DefaultAzureCredential used
0%
100%
AzureSemanticVadTurnDetection
0%
100%
Without context: $0.5611 · 5m 7s · 21 turns · 24 in / 10,888 out tokens
With context: $0.7955 · 6m 55s · 36 turns · 132 in / 10,144 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
Table of Contents
Is this your skill?
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.