Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.praison.ai/llms.txt

Use this file to discover all available pages before exploring further.

Text-to-Speech using Vertex AI Gemini models.

​
Setup

export GOOGLE_APPLICATION_CREDENTIALS=path/to/service-account.json
# or
export VERTEXAI_PROJECT=your-project-id
export VERTEXAI_LOCATION=us-central1

​
Usage

from praisonaiagents import AudioAgent

agent = AudioAgent(llm="vertex_ai/gemini-2.5-flash-preview-tts")
agent.speech("Hello world!", output="hello.mp3")

​
Models

ModelDescription
vertex_ai/gemini-2.5-flash-preview-ttsGemini TTS