Text to speech

Asked on 2025-07-14

1 search

Apple introduced a new API called Speech Analyzer at WWDC 2025, which enhances the speech-to-text capabilities across its platforms. This API is designed to support a wide range of use cases, including long-form and distant audio such as lectures, meetings, and conversations. It leverages the power of Swift to perform speech-to-text processing on-device with minimal code.

The Speech Analyzer API includes a new speech-to-text model that is faster and more flexible than previous models. It is already being used in system apps like Notes, Voice Memos, and FaceTime for features such as live captions and call transcription. The API allows developers to build similar features into their own applications.

For more detailed information, you can refer to the session titled "Bring advanced speech-to-text to your app with SpeechAnalyzer" from WWDC 2025. This session covers the API's design, its capabilities, and provides a live coding demo. You can start exploring this session from the SpeechAnalyzer API chapter.