What is SpeechAnalyzer?

SpeechAnalyzer is a new API introduced by Apple in iOS 26, designed to enhance speech-to-text capabilities across all Apple platforms. It leverages the power of Swift to perform speech-to-text processing and manage model assets on the user's device with minimal code. The API is part of Apple's effort to support more use cases and improve upon the previous SF Speech Recognizer, which was limited to short-form dictation and required user intervention to add languages.

The SpeechAnalyzer API is accompanied by a new speech-to-text model called SpeechTranscriber, which is faster and more flexible than its predecessor. This model is particularly effective for long-form and distant audio, such as lectures, meetings, and conversations. It is already being used in various system apps like Notes, Voice Memos, and FaceTime for features like call summarization and live captions.

The API consists of the SpeechAnalyzer class and several other classes, allowing developers to create transcription sessions that process audio asynchronously. This enables applications to handle audio input and transcription results independently, providing a seamless user experience.

For more details, you can refer to the session Bring advanced speech-to-text to your app with SpeechAnalyzer (02:41).