메뉴
Build real-time voice AI applications with bidirectional WebSocket communication.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/BEKO2210/Firstbrain --skill azure-ai-voicelive-py명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | azure-ai-voicelive-py |
| description | Build real-time voice AI applications with bidirectional WebSocket communication. |
| type | skill |
| created | 2026-02-27T00:00:00.000Z |
| domain | cloud-infrastructure |
| category | azure |
| risk | unknown |
| source | community |
| tags | ["skill","cloud-infrastructure","azure","voicelive"] |
Build real-time voice AI applications with bidirectional WebSocket communication.
pip install azure-ai-voicelive aiohttp azure-identity
AZURE_COGNITIVE_SERVICES_ENDPOINT=https://<region>.api.cognitive.microsoft.com
# For API key auth (not recommended for production)
AZURE_COGNITIVE_SERVICES_KEY=<api-key>
DefaultAzureCredential (preferred):
from azure.ai.voicelive.aio import connect
from azure.identity.aio import DefaultAzureCredential
async with connect(
endpoint=os.environ["AZURE_COGNITIVE_SERVICES_ENDPOINT"],
credential=DefaultAzureCredential(),
model="gpt-4o-realtime-preview",
credential_scopes=["https://cognitiveservices.azure.com/.default"]
) as conn:
...
API Key:
from azure.ai.voicelive.aio import connect
from azure.core.credentials import AzureKeyCredential
async with connect(
endpoint=os.environ["AZURE_COGNITIVE_SERVICES_ENDPOINT"],
credential=AzureKeyCredential(os.environ["AZURE_COGNITIVE_SERVICES_KEY"]),
model="gpt-4o-realtime-preview"
) as conn:
...
import asyncio
import os
from azure.ai.voicelive.aio import connect
from azure.identity.aio import DefaultAzureCredential
async def main():
connect(
endpoint=os.environ[],
credential=DefaultAzureCredential(),
model=,
credential_scopes=[]
) conn:
conn.session.update(session={
: ,
: [, ],
:
})
event conn:
()
event. == :
()
event. == :
asyncio.run(main())
The VoiceLiveConnection exposes these resources:
| Resource | Purpose | Key Methods |
|---|---|---|
conn.session | Session configuration | update(session=...) |
conn.response | Model responses | create(), cancel() |
conn.input_audio_buffer | Audio input | append(), commit(), clear() |
conn.output_audio_buffer | Audio output | clear() |
conn.conversation | Conversation state | item.create(), item.delete(), item.truncate() |
conn.transcription_session | Transcription config | update(session=...) |
from azure.ai.voicelive.models import RequestSession, FunctionTool
await conn.session.update(session=RequestSession(
instructions="You are a helpful voice assistant.",
modalities=["text", "audio"],
voice="alloy", # or "echo", "shimmer", "sage", etc.
input_audio_format="pcm16",
output_audio_format="pcm16",
turn_detection={
"type": "server_vad",
"threshold": 0.5,
"prefix_padding_ms": 300,
"silence_duration_ms": 500
},
tools=[
FunctionTool(
type="function",
name="get_weather",
description="Get current weather",
parameters={
"type": "object",
"properties": {
"location": {"type": "string"}
},
"required": ["location"]
}
)
]
))
import base64
# Read audio chunk (16-bit PCM, 24kHz mono)
audio_chunk = await read_audio_from_microphone()
b64_audio = base64.b64encode(audio_chunk).decode()
await conn.input_audio_buffer.append(audio=b64_audio)
async for event in conn:
if event.type == "response.audio.delta":
audio_bytes = base64.b64decode(event.delta)
await play_audio(audio_bytes)
elif event.type == "response.audio.done":
print("Audio complete")
async for event in conn:
match event.type:
# Session events
case "session.created":
print(f"Session: {event.session}")
case "session.updated":
print("Session updated")
# Audio input events
case "input_audio_buffer.speech_started":
print(f"Speech started at {event.audio_start_ms}ms")
case "input_audio_buffer.speech_stopped":
print(f"Speech stopped at {event.audio_end_ms}ms")
# Transcription events
case "conversation.item.input_audio_transcription.completed":
print(f"User said: {event.transcript}")
case "conversation.item.input_audio_transcription.delta":
print(f"Partial: {event.delta}")
# Response events
case "response.created":
print(f"Response started: {event.response.id}")
case "response.audio_transcript.delta":
print(event.delta, end="", flush=True)
case "response.audio.delta":
audio = base64.b64decode(event.delta)
case "response.done":
print(f"Response complete: {event.response.status}")
# Function calls
case "response.function_call_arguments.done":
result = handle_function(event.name, event.arguments)
await conn.conversation.item.create(item={
"type": "function_call_output",
"call_id": event.call_id,
"output": json.dumps(result)
})
await conn.response.create()
# Errors
case "error":
print(f"Error: {event.error.message}")
await conn.session.update(session={"turn_detection": None})
# Manually control turns
await conn.input_audio_buffer.append(audio=b64_audio)
await conn.input_audio_buffer.commit() # End of user turn
await conn.response.create() # Trigger response
async for event in conn:
if event.type == "input_audio_buffer.speech_started":
# User interrupted - cancel current response
await conn.response.cancel()
await conn.output_audio_buffer.clear()
# Add system message
await conn.conversation.item.create(item={
"type": "message",
"role": "system",
"content": [{"type": "input_text", "text": "Be concise."}]
})
# Add user message
await conn.conversation.item.create(item={
"type": "message",
"role": "user",
"content": [{"type": "input_text", "text": "Hello!"}]
})
await conn.response.create()
| Voice | Description |
|---|---|
alloy | Neutral, balanced |
echo | Warm, conversational |
shimmer | Clear, professional |
sage | Calm, authoritative |
coral | Friendly, upbeat |
ash | Deep, measured |
ballad | Expressive |
verse | Storytelling |
Azure voices: Use AzureStandardVoice, AzureCustomVoice, or AzurePersonalVoice models.
| Format | Sample Rate | Use Case |
|---|---|---|
pcm16 | 24kHz | Default, high quality |
pcm16-8000hz | 8kHz | Telephony |
pcm16-16000hz | 16kHz | Voice assistants |
g711_ulaw | 8kHz | Telephony (US) |
g711_alaw | 8kHz | Telephony (EU) |
# Server VAD (default)
{"type": "server_vad", "threshold": 0.5, "silence_duration_ms": 500}
# Azure Semantic VAD (smarter detection)
{"type": "azure_semantic_vad"}
{"type": "azure_semantic_vad_en"} # English optimized
{"type": "azure_semantic_vad_multilingual"}
from azure.ai.voicelive.aio import ConnectionError, ConnectionClosed
try:
async with connect(...) as conn:
async for event in conn:
if event.type == "error":
print(f"API Error: {event.error.code} - {event.error.message}")
except ConnectionClosed as e:
print(f"Connection closed: {e.code} - {e.reason}")
except ConnectionError as e:
print(f"Connection error: {e}")
This skill is applicable to execute the workflow or actions described in the overview.