TTS (Text-to-Speech) in AgentScope

This example demonstrates how to integrate DashScope Realtime TTS model with ReActAgent to enable audio output. The agent can speak its responses in real-time.

This example uses DashScope's Realtime TTS model, you can also change to other TTS models supported by AgentScope, e.g. OpenAI, Gemini, etc.

To run the example, execute:

python main.py