GPT Audio performance data on Rival is based on blind head-to-head community voting. Overall win rate: 50.0% across 4 duels. All vote data is part of Rival's open dataset of 21,000+ human preference judgments across 200+ AI models. Model responses are curated from 6 challenges.
OpenAI's first generally available audio model. Features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Supports both text and audio input/output.
Use GPT Audio in your applications via the OpenRouter API. Copy the code below to get started.
import requests
response = requests.post(
"https://openrouter.ai/api/v1/chat/completions" ,
headers={
"Authorization""Bearer $OPENROUTER_API_KEY" : ,
"Content-Type""application/json" :
},
json={
"model""openai/gpt-audio" : ,
"messages""role""user""content""Hello!" : [{: , : }]
}
)
print(response.json())Replace $OPENROUTER_API_KEY with your API key from openrouter.ai/keys
6 outputs from GPT Audio
Character Voice Dialogue
Narrator Storytelling
Podcast Introduction
Emotional Monologue
News Anchor Bulletin
Multilingual Greeting
Try GPT Audio
We're not suggesting you leave GPT Audio. We're just... putting these here. In case you're curious. Which you are, because you scrolled this far.