Menu
Build real-time voice AI applications with bidirectional WebSocket communication.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/BEKO2210/Firstbrain --skill azure-ai-voicelive-pyThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| 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.