voice interaction Archives

AppWizard

May 2, 2025

How to use Gemini Live’s camera and screen sharing features

Gemini Live has transitioned from a voice-based AI assistant to a multimodal platform that can process camera feeds and screen-sharing inputs, enhancing user interactions with visual context. It requires an Android device with at least 2 GB of RAM and Android 10 or later, along with a Google One AI Premium subscription for access to camera and screen-sharing features. These features are complimentary for Google Pixel 9 and Samsung Galaxy S25 users, and newer Pixel devices may offer a trial for Gemini Advanced. To share a live video feed, users must launch Gemini, tap the Live icon, select the Camera button, and ensure the desired items are visible. For screen sharing, users open the relevant app or screen, activate Gemini, and select Share screen with Live. Gemini can summarize content and answer questions based on the shared screen. The multimodal capabilities are particularly beneficial for scenarios requiring detailed descriptions, positioning Gemini Live competitively alongside other AI platforms.

Winsage

March 31, 2025

Announcing Windows 11 Insider Preview Build 22635.5160 (Beta Channel)

Windows 11 Insider Preview Build 22635.5160 (KB5053654) has been released for the Beta Channel for users on Windows 11, version 23H2. Windows 11, version 24H2 is also available as an optional upgrade for Insiders in the Beta Channel. New features include: - A speech recap feature in Narrator that allows users to track and reference spoken content, with a history of the last 500 strings spoken. Users can access this feature using keyboard shortcuts. - Copilot on Windows can now be launched with Win + C, and users can customize their Copilot key. It includes a press-to-talk feature for voice interaction. - The Windows share window has been enhanced to allow quick editing options for images, including cropping and applying filters. - A new FAQs section has been added to the Settings > System > About page to provide users with quick answers about their PC. Fixes include resolving delays in app icons appearing in the Start menu and updating the logic for desktop app icons to enhance visibility. Known issues include a flashing context menu in the Start menu and a crash issue with Narrator that can be resolved by restarting the PC. Windows Insiders in the Beta Channel will receive updates based on Windows 11, version 23H2 through an enablement package, and features are rolled out gradually using Controlled Feature Rollout technology.

Winsage

March 11, 2025

You can ‘Press to Talk’ to Copilot via a Windows hotkey now

Microsoft Copilot now offers complimentary unlimited access to its top two features for all users. A new feature called Press to Talk has been introduced in the latest Windows 11 Insider build, allowing users to initiate voice chat by holding down the Alt key and the Spacebar for two seconds. If there is a pause in conversation, the AI will automatically conclude the chat, and pressing the Esc key will end the interaction. Users can customize Copilot's voice and settings through the Copilot web page. The update (version 1.25024.100.0 and higher) is being gradually rolled out to Windows Insiders, with a potential transition to the production version of Windows expected based on user feedback.

Winsage

March 11, 2025

Windows 11 will add a new way to talk to Microsoft Copilot — no Copilot key required

Microsoft is testing a new press to talk functionality for its Copilot feature on PCs, allowing users to engage with the AI tool using a keyboard shortcut (Alt + Spacebar for two seconds) to start a voice conversation and Esc to end it. The update is being rolled out via the Microsoft Store, requiring the app version to be at least 1.25024.100.0. Additionally, a revamped Copilot app for Windows 11 is being previewed, featuring a native app UI framework for better integration, faster launch times, and the option to start automatically upon boot. Some users have expressed surprise at the chosen keyboard shortcut, suggesting a preference for a dedicated Copilot key.

Winsage

March 11, 2025

Copilot on Windows: Press to talk begins rolling out to Windows Insiders

Windows Insiders can now access an updated Microsoft Copilot app through the Microsoft Store, featuring enhancements for user interaction and functionality. A key new feature is the voice interaction capability, which allows users to start a voice conversation by holding down the Alt + Spacebar for two seconds. To end the conversation, users can press the Esc key, and the session will automatically conclude after a pause. The update, version 1.25024.100.0 and higher, is being rolled out gradually across Insider Channels. Users are encouraged to provide feedback through the Feedback Hub or within the Copilot app.

Winsage

March 11, 2025

Windows’ Cortana is back from the dead, and you’re not going to like her new form

Cortana has been reintroduced as Copilot, which allows voice interaction through a hotkey. The Copilot update features voice commands and a microphone icon, aiming to enhance productivity in Windows 11. Users can engage with Copilot by holding the Alt + Spacebar for two seconds and can end the conversation by pressing the Esc key. Unlike Cortana, Copilot does not permit users to adjust system settings via voice commands; instead, it directs users to the Copilot app for interaction.

Winsage

October 17, 2024

The New Windows 11 24H2 Version Is Out, Here’s What’s Changed on Our Computers – Jason Deegan

Microsoft has released Windows 11 Version 24H2, featuring significant updates including: - Enhanced Energy Saver Mode that optimizes battery life for laptops by limiting background processes and reducing CPU usage. - Improved smartphone integration through the updated "Phone Link" app, allowing smartphones to be used as webcams and providing quick access to mobile app features from the desktop. - A more customizable Start menu, enabling users to pin applications to the taskbar and access Microsoft account information directly. - Noteworthy enhancements to File Explorer, including native support for 7zip and TAR formats, performance optimizations for ZIP file extraction, and improved navigation features. - A more user-friendly Quick Settings menu with easier scrolling, customizable arrangements, and a refresh button for Wi-Fi networks. - Support for HDR wallpapers, allowing the use of .JXR format images and automatic adjustments between HDR and SDR displays. - Support for Wi-Fi 7 and Bluetooth LE Audio, enhancing connectivity options and introducing features for hearing aid users. - Voice Clarity feature that reduces background noise during voice calls using AI technology. - New Copilot+ features, including voice interaction, personalized news summaries, enhanced AI capabilities for complex queries, smarter browsing in Edge, and improved memory function for sensitive data. Users can manually initiate the update by navigating to Settings > Update & Security if it does not prompt automatically.

AppWizard

October 10, 2024

Google Gemini has gotten a facelift on Android — here’s what has changed

Google has rolled out a new design for the Google Gemini app on Android devices, addressing previous criticisms of its cluttered interface. The updated app features a simple welcome message, a small chat bubble for easy access to chat history, and a redesigned text input field that resembles natural conversation flow. The microphone and camera options are now integrated into the streamlined design, and the Gemini Live waveform feature has been moved to the bottom right corner for better accessibility. Additionally, Google has introduced the Gemini Live Voice Mode, allowing real-time conversations with the app at no cost. This redesign aims to enhance usability and attract users who were previously deterred by outdated information. A curated list of engaging prompts is also available to help users maximize their experience with the new app.

Winsage

October 2, 2024

‘Comfortable, fun, familiar’: Why Microsoft is trying to turn its AI chatbot into a digital friend | CNN Business

Artificial intelligence chatbots are being developed to assist users with various tasks, but many find them rigid and overly formal. Microsoft is enhancing its chatbot, Copilot, to create a more engaging experience by introducing features like real-time voice interactions and the ability to interpret images and text. The updated Copilot aims to communicate in a warm tone and provide emotional support, distinguishing itself in a competitive market. Microsoft envisions Copilot as a digital companion that integrates into users' lives, offering assistance beyond productivity. The company has addressed previous criticisms of its chatbot by refining its responses and hiring voice actors to create distinct voice options. New features include a daily function for weather and news updates, integration with the Edge browser, and a testing platform called "Copilot Labs" for users to explore upcoming functionalities. Microsoft assures that privacy concerns related to data retention have been addressed with the new Copilot Vision feature.