azure-ai-voicelive-py

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with...

Install with Tessl CLI

npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-voicelive-py

What are skills?

1.46x

Review — 81%

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/skill

Learn more

Evaluation — 95%

↑ 1.46x

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

18%

Voice Assistant with Live Tool Lookup

Function calling and session configuration

Criteria

Without context

With context

Correct import module

100%

Async context manager

100%

gpt-4o-realtime-preview model

100%

DefaultAzureCredential used

100%

credential_scopes parameter

100%

FunctionTool import and usage

100%

Session update with tools

100%

Text and audio modalities

100%

Event loop pattern

100%

Function call output item

100%

response.create after function output

100%

asyncio entry point

100%

Without context: $0.9230 · 6m 21s · 41 turns · 450 in / 7,299 out tokens

With context: $0.3213 · 2m 33s · 19 turns · 23 in / 3,648 out tokens

87%

18%

Batch Audio Transcription and Response Tool

Manual turn control and audio streaming

Criteria

Without context

With context

Correct import path

100%

Async context manager

60%

100%

base64 encoding for audio

100%

input_audio_buffer.append usage

40%

100%

turn_detection disabled

100%

Manual commit

66%

100%

Explicit response trigger

60%

100%

Conversation item injection

12%

Transcript event handling

70%

50%

PCM16 audio format specification

100%

Event loop pattern

100%

asyncio entry point

100%

Without context: $0.6353 · 7m 8s · 34 turns · 73 in / 8,633 out tokens

With context: $0.4104 · 3m 32s · 23 turns · 27 in / 4,065 out tokens

100%

55%

Resilient Call Center Voice Agent

Interrupt handling, error handling, and semantic VAD

Criteria

Without context

With context

Correct import path

100%

ConnectionClosed import

100%

ConnectionError import

100%

Separate exception handlers

100%

Try/except around connect block

62%

100%

Azure Semantic VAD type

100%

Telephony audio format

100%

Barge-in: response.cancel()

50%

100%

Barge-in: output buffer clear

50%

100%

Event loop pattern

40%

100%

asyncio entry point

100%

DefaultAzureCredential or AzureKeyCredential

100%

Without context: $0.8317 · 8m 2s · 35 turns · 38 in / 14,069 out tokens

With context: $0.4281 · 3m 14s · 22 turns · 27 in / 4,629 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Voice Assistant with Live Tool Lookup Batch Audio Transcription and Response Tool Resilient Call Center Voice Agent

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.