What is the speech recognition api?

Asked on 2026-02-12

1 search

The Speech Recognition API discussed at WWDC is the new Speech Analyzer API, introduced in iOS 26. This API is 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 Speech Analyzer API is more versatile than its predecessor, the SFSpeechRecognizer, and is suitable for a wider range of use cases, including long-form and distant audio such as lectures, meetings, and conversations.

The Speech Analyzer API is already integrated into several system apps like Notes, Voice Memos, and Journal, and it supports features like call summarization and live transcription. The API consists of the Speech Analyzer class and several other classes, allowing developers to add modules for specific types of analysis, such as transcription.

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