Sobes Copilot қолданбасын жүктеп алыңыз

Шағын түзетулер мен жақсартулар

⌨️ Added a hotkey for switching models

The hotkey can switch models only within the current provider or cycle through all available models – you can select the desired mode in the settings.

There is no standard combination – you can create a convenient hotkey in the settings.

💼 Added the ability to specify a vacancy for existing meetings

Now you can specify a vacancy not only when creating a meeting, but also add it to an existing one.

After saving, the information will automatically update in the interview tracker, so you don't have to edit the meeting in multiple places.

🧠 Removed the Knowledge Base

Unfortunately, the Knowledge Base didn't live up to expectations.

In practice, it often added unnecessary delays rather than speeding up responses, so we decided not to keep this feature for the sake of adding features and removed it from the app entirely.

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

We've updated the model selection and added AI reasoning levels.

🧠 Control the depth of your answer

You can now select the reasoning level before generating a response: off, low, medium, high, or maximum.

The higher the level, the longer it takes to generate a response, but the higher its quality.

By default, reasoning is off—quick answers will remain fast.

⏱ Speed ​​​​is immediately visible

The model selection displays the estimated time until the answer starts, separately for each reasoning level.

For simple questions, you can leave reasoning off, and for complex tasks, code, and system design, select high or maximum.

⚡ Works with quick actions and hotkeys

The selected model and reasoning level can be saved for quick actions or assigned to a hotkey.

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

🔊 Added AI voiceover

We hope you'll never need this, but if you're asked to answer with your eyes closed during an interview, the app has a plan for that too.

You can turn voiceover on or off using the hotkey Ctrl/Cmd + Shift + S.

You can also turn voiceover on automatically: a new AI response will begin playing automatically when the first character of the answer appears.

A separate hotkey, Ctrl/Cmd + Alt/Option + S, is available to turn automatic voiceover on and off.

🛠 Voiceover Settings

In the settings, you can select the voiceover, volume, speech rate, left/right balance, output device, and immediately test your voice with a short test phrase.

🧹 Added auto-collapse of recent groups

We've added the ability to automatically collapse recent transcript groups and tool calls. It can be enabled in the settings, in the "Chat" section.

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

🎨 Redesigned Main Screens

We've completely updated the design of the app login, meeting list, settings, and many other interface elements.

🔠 Added text resizing in chats

You can now change the text size in chats separately from the overall app size. If you wanted to make messages larger or more compact without affecting the entire interface, you can now do so normally.

🔔 Redesigned Update Notifications

The update notification no longer takes up the entire screen. Instead, it appears as a discreet button in the main window header—it's noticeable but doesn't interfere with your work.

🕵️ Improved App Cloaking

We've redesigned the app cloaking algorithm on macOS and added 33 new presets.

🎙 Fixes in interview recordings

• Fixed an issue with audio desync in very long interview recordings.

• Fixed audio recording stopping when changing the output device.

📝 Improved meeting summary handling Added the ability to start summary generation directly from the meeting list. It's also now clear whether a summary has already been generated, and if it's already being generated, it's displayed correctly.

⚡️ Speed ​​up generation start

Screenshots outside of quick actions are now preloaded before sending a message.

This allows generation to start faster: the app doesn't have to wait for the screenshot to load when starting generation.

🎨 Fixed the canvas in the design system

Fixed an issue where the canvas in the design system would forget its position and scale when hiding and reopening the overlay.

🎙 Reworked the audio recording module

It is now faster, uses less CPU and RAM, and supports more devices. This should improve recording stability, especially on laptops and non-standard audio configurations.

⌨️ Updated meta key blocker

It now works correctly with both left and right Shift, Alt, Ctrl, Cmd, and Opt keys.

🛠 Minor fixes in the interview tracker

We also fixed several minor issues in the interview tracker.

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

Шағын түзетулер мен жақсартулар

🎙 Showed transcription modes

The list of transcription models now displays the available modes: Async and Realtime.

📁 Improved saving of interview recordings

Interview recordings are now saved in a folder with the meeting name, rather than a folder with a random ID.

⌨️ Added hotkey display in the HUD

The HUD now displays hotkeys for disabling click-to-close, cursor protection, and the virtual cursor.

🔔 Fixed the recording start notification

Fixed an issue where the recording start notification could not be closed manually.