Galaxy Watch enthusiasts can look forward to an enhanced text-to-speech (TTS) experience as Google introduces a new TTS engine tailored for Wear OS 4. This innovation focuses on using advanced machine learning models with reduced prosody, designed to accelerate the synthesis of speech on wearable devices. Additionally, Google has optimized the engine to ensure it delivers high performance and reliability, even on devices with limited memory capacity.
The implementation of this new TTS engine should notably improve the user experience on devices like the Galaxy Watch 4, Watch 5, and upcoming Watch 6 models. Users can expect quicker TTS functionality alongside reduced resource consumption, potentially contributing to enhanced device performance and longer battery life. Details regarding the exact rollout of the engine are pending, but it is anticipated that it will be included in an upcoming system update.
After booting up a device, the upgraded TTS engine should be ready within 10 seconds. Google has clarified that its primary use cases will be for brief interactions. This includes features such as providing accessibility support, exercise coaching cues, navigation directions, and the vocalization of alerts via the watch speaker or Bluetooth-connected headphones. Longer readings, such as detailed articles or lengthy podcast summaries, are not recommended uses for the TTS engine due to its design for short-term interactions.
In terms of language support, Google has announced that the engine will cater to more than 50 languages. By default, seven languages—English, Spanish, French, Italian, German, Japanese, and Mandarin Chinese—will come pre-installed, although manufacturers can choose an alternative selection to pre-load. For users selecting a language not included by default, the smartwatch will automatically download the necessary language pack when connected to Wi-Fi and on charge during the setup process.
With these improvements, Galaxy Watch users can anticipate a more responsive and efficient user experience when interacting with TTS-related features on their wearables.
