Skip to main content
Audio processing using Azure OpenAI services.

​
Setup

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

​
Text-to-Speech

from praisonaiagents import AudioAgent

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

​
Speech-to-Text

from praisonaiagents import AudioAgent

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

​
Models

ModelType
azure/tts-1TTS
azure/tts-1-hdTTS HD
azure/whisperSTT