Introducing next-generation audio models in the API

OpenAI has released next-generation audio models in its API.

The new gpt-4o-transcribe and gpt-4o-mini-transcribe models improve speech recognition accuracy and language detection.

The text-to-speech side also adds more natural, customizable speaking styles.

OpenAI says the models outperform Whisper on benchmarks and are built for more reliable voice applications.