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.

Audio processing using Google’s Gemini models.

​
Setup

export GOOGLE_API_KEY=your-key

​
Text-to-Speech

from praisonaiagents import AudioAgent

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

​
Speech-to-Text

from praisonaiagents import AudioAgent

agent = AudioAgent(llm="gemini/gemini-2.0-flash")
text = agent.transcribe("audio.mp3")
print(text)

​
Models

ModelType
gemini/gemini-2.5-flash-preview-ttsTTS
gemini/gemini-2.0-flashSTT