- Fixes an error alert that could occur when downloading the local model

■ Improved • You can toggle off the summary view on the homescreen • When adding an API key, it’s automatically enabled ■ Bugfixes • Fixed an issue where if you didn’t have an AI service setup, you could get an error alert when creating a summary

■ Improved • Small tweaks and design improvements on iPadOS

■ New • Implemented a new Liquid Glass design • You can now browse your old transcriptions and dictations • Added support for Apple Foundation Models to be used for AI features • Added support for the new on device transcription engine • A short summary is now autogenerated if you have an AI service setup • You can adjust the prompt that is used for the long summary • Added initial support for Shortcuts. We’ll add more soon. • Recordings are automatically saved, even if they fail for some reason. ■ Improved • The app is now much faster to use • Added support for more apps for the dictation keyboard ■ Fixed • Fixed an issue where a recording would not be saved

■ Fixed • Fixed an issue where the local model could not be downloaded

■ Improvements • Added support for more apps for the keyboard feature ■ Fixed • Fixed a crash that could happen when running the app from a locked phone state

■ Improvements • Added a check for minimum available storage space before you can download a local model. This could lead to crashes when downloading without having enough space. • Cleaned up the dictation history detail view • Improved dictation support for Microsoft Teams, Outlook, Claude, Drafts 5 and more. ■ Fixed • Disabled swiping in the keyboard setup view

■ New • This update introduces a new dictation keyboard you can use in any app on your iOS device! Simply select it from the Globe icon after setting it up and you can talk much faster than you can type all across the system. Let us know how it works for you. We’ll be improving it a lot over the next few weeks based on your feedback!

Fixed an issue where the summary could be shown in the incorrect order

■ Fixed • It was possible for transcription segments to sometimes be displayed in the wrong order when transcribed on-device.

■ New • Added support for videos • Improved performance for local models ■ Improvements • Improved support for files that were stored in iCloud when shared with the app • Audio playback improvements

■ New • Your transcriptions and recordings are now saved in the new history view. Quickly revisit previous transcriptions without having to transcribe them again ■ Improvements • Improved design stuff all around the app, making it more clean and simple • If you’re playing music it will no longer be paused when you get to the transcription view • Added a “Are you sure you want to quit alert” to prevent data loss • Clearer error alerts with simpler descriptions ■ Bugfixes • Voice Memos audio files no longer show the WhatsApp icon • Fixed an issue where the summary could be presented out of order

■ Improvements • Improved the German, Dutch & French localisation • More accurately show the origin app of the file you share to the app

■ Improvements • Improved the navigation flow of the app while transcribing files from other apps ■ Bugfixes • Due to technical changes the file size limit for cloud transcription is 50MB right now. We’re looking into more ways to increase this.

■ New • Added control center, lock screen and homescreen widgets to start a recording ■ Improvements • Increased the file size limit for cloud transcription to 1GB to support larger files • Added support for iPad Air M1 for local models

Fixed an issue where you could not record the microphone

■ New • Added homescreen and control center widgets to quickly start a new recording • You can now export recordings before you start transcribing them ■ Improvements • Increased line spacing on the transcript view for a more calm look and feel • Recordings start immediately on the record screen now • Fixed dark mode colors in onboarding

■ New • You can now add your own API keys for OpenAI and ElevenLabs. Use them to transcribe and chat with your transcripts. Thanks for all the feedback, more fixes and improvements are coming soon!

■ Improvements • Added a yearly subscription option, thanks for the feedback!

■ Improvements • Improved the design of the chat screen ■ Bugfixes • Fixed an issue where you could not prompt your transcript • Fixed an issue where unsupported devices (iPhone 12 and iPad Air M1) could see local models even though they are not supported

■ Improvements • The prompt textfield gets cleared when you send your prompt • Performance improvements

■ Improvements • Added support for local models for iPhone 13 and newer • Made it clearer that you can use local models for free

■ Improvements • Improved model downloading on iPad