> ## 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.

# OpenAI Audio

> TTS and Whisper

## Text-to-Speech

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import AudioAgent

agent = AudioAgent(llm="openai/tts-1")
agent.say("Hello!", output="hello.mp3")
```

## Speech-to-Text

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import AudioAgent

agent = AudioAgent(llm="openai/whisper-1")
text = agent.listen("audio.mp3")
print(text)
```

## TTS Models

| Model                    | Quality      |
| ------------------------ | ------------ |
| `openai/tts-1`           | Standard     |
| `openai/tts-1-hd`        | High quality |
| `openai/gpt-4o-mini-tts` | Latest       |

## Voices

`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`