OpenAI: GPT Audio
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
What it costs
$5 per 1M tokens in · $20 per 1M out
Where it runs
A language model that returns media — billed per token like any other model, on the same key.
Subscribe to new models