azure-ai-voicelive-py

Resultado esperado:

Use DefaultAzureCredential for production authentication: ```python
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:
# Use connection
```

Resultado esperado:

Azure Voice Live supports these built-in voices: alloy (neutral), echo (warm), shimmer (professional), sage (authoritative), coral (friendly), ash (deep), ballad (expressive), verse (storytelling). Azure also provides AzureStandardVoice, AzureCustomVoice, and AzurePersonalVoice models.

Resultado esperado:

Handle interruptions by listening for speech_started events and canceling the current response: ```python
async for event in conn:
if event.type == 'input_audio_buffer.speech_started':
await conn.response.cancel()
await conn.output_audio_buffer.clear()
```