Azure Audio

TTS and STT with Azure

Audio processing using Azure OpenAI services.

Setup

bash

export AZURE_API_KEY=your-key
export AZURE_API_BASE=https://your-resource.openai.azure.com

python

from praisonaiagents import AudioAgent

agent = AudioAgent(llm="azure/tts-1")
agent.speech("Hello world!", output="hello.mp3")

python

from praisonaiagents import AudioAgent

agent = AudioAgent(llm="azure/whisper")
text = agent.transcribe("audio.mp3")
print(text)