OpenAI
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...
| Specifications | |
|---|---|
| Provider | OpenAI |
| Input pricing | $2.50/M tokens |
| Output pricing | $10.00/M tokens |
| Context length | 128K tokens |
| Max output | 16K tokens |
| Input modalities | textaudio |
| Output modalities | textaudio |
| Tokenizer | GPT |
| Content moderated | Yes |
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p