Release 1.3.1: Advanced Developer Features & Audio Processing Refinements

• Automated Build Pipeline: Shell scripts for notarization and compilation have been fully automated, significantly reducing deployment time and eliminating manual steps in the release process.
• Voice Activity Detection Improvements: Refined VAD confidence threshold algorithm provides more accurate detection of speech in challenging acoustic environments.
• Simplified Call Interface: Removed X/hide functionality to create a cleaner, more intuitive UI for ending calls, resulting in fewer accidental disconnections.
• Extended Bit Depth Compatibility: Added support for both 16-bit and 24-bit audio devices, ensuring compatibility with professional recording equipment and high-fidelity input sources.
• Advanced Diagnostic Logging: Implemented detailed optional logging for troubleshooting complex audio routing scenarios.
• Cross-platform Consistency: Unified the user experience across different operating systems with standardized audio handling.

Release 1.2.8: Streamlined Experience & Advanced Audio Selection

• Skip Onboarding Option: New users can now bypass the initial setup process with a single click, ideal for experienced users or quick deployment scenarios.
• Streamlined Tutorial Flow: We've removed the demo section from the onboarding tutorial, creating a more efficient and focused learning experience.
• Audio Device Selection: Users can now manually select their preferred input and output devices from a comprehensive dropdown menu for precise audio control.
• Enhanced Translation Model: All conversations now default to our most robust neural translation model, delivering superior accuracy for complex terminology and nuanced expressions.
• Performance Optimization: Background processes have been refined to reduce memory usage and improve overall responsiveness.
• Extended Device Compatibility: Support added for a wider range of professional audio interfaces and legacy hardware.
• Fine-tuned Error Handling: Improved detection and helpful guidance for resolving common configuration issues without technical knowledge.

Release 1.2.4: Mandatory Audio Driver Update & Enhanced Stability

• Mandatory Audio Driver Update: Ensuring optimal performance by requiring the latest driver updates before using the app.
• Automated Troubleshooting: If a driver issue is detected, users will be prompted to reinstall the app for a seamless fix.
• Automatic Gain Control (AGC) v2: Dynamically adjusts input volume for clearer audio without distortion.
• Refined Virtual Microphone (Vmic) Detection: The "Show me how" button will no longer appear if a virtual mic is detected.
• Reinstated Disclaimer Sound: Plays per session unless explicitly disabled.
• Improved Compatibility Checks: Detects whether the default browser is Gecko or WebKit-based for optimized performance.
• Enhanced Audio Engine: Refactored looper and introduced a driver blacklist to prevent conflicts with virtual audio devices.

Release 1.2.0: New Thread Model & Virtual Audio Improvements

• New Thread Model for Audio Processing: Improved efficiency in handling input/output streams.
• Optimized Software Audio Mixer: Enhances performance when handling multiple audio sources.
• UI Enhancements: Fixed layout height issues, optimized onboarding screens, and added an export icon when a call finishes.
• Improved Echo Cancellation for Windows: Adjusted hyperparameters for better feedback suppression.
• Bug Fixes: Resolved issues with stacked boxes, error messages, and compatibility with different operating systems.

Release 1.1.13: Smart Call Behavior & Echo Cancellation v5

• Adaptive Echo Cancellation: Improved real-time adjustments to eliminate feedback loops more effectively.
• Smart Call Behavior: Calls will now automatically end after 15 minutes of inactivity.
• New Use Case Defaults: Removed the use case selection page from onboarding and set the default to "Family/Friends."
• Improved Virtual Audio Device Handling: Unmuting behavior for virtual devices now works consistently across platforms.
• Enhanced UI Responsiveness: Fixed issues with combo box sizes and improved general layout responsiveness.

Release 1.1.10: Multi-Platform Audio Enhancements

• Cross-Platform Virtual Audio Support: Improved handling of virtual drivers like VB-Audio and BlackHole.
• Windows & macOS Driver Optimizations: Enhanced device selection flow for better compatibility.
• New Language Support: Introduced audio driver support for additional languages.
• Streamlined Onboarding: Removed the testing area from onboarding and introduced a simplified initial configuration.

Release 1.1.7: Audio Mixer Refinements & Performance Boost

• Updated Audio Buffering System: Reduces latency when handling multiple audio sources.
• Bug Fixes & Stability Improvements: Fixed issues related to sleep logic and UI inconsistencies.
• Enhanced Volume Control: Refactored auto-gain algorithm to allow manual toggling per track.
• New Logging & Debugging Features: Introduced advanced logging tools for internal diagnostics.

Release 1.1.5: Audio Processing Overhaul & UX Improvements

• Dynamic Noise Suppression: Improves clarity in environments with unpredictable background noise.
• Virtual Mic Enhancements: Added checks to detect VB-Audio and similar virtual drivers to prevent conflicts.
• Refactored Audio Pipeline: Significant improvements in echo cancellation and auto-gain control.
• UI Streamlining: Improved settings navigation and error handling.

Release 1.1.2: Echo Cancellation v4 & Refinements

• Further Echo Cancellation Enhancements: Refinements to prevent residual echoes and improve background noise suppression.
• UI Simplifications: Removed unnecessary UI elements and improved default settings for first-time users.
• Mac Compatibility Fixes: Addressed issues with input/output volume inconsistencies.
• Performance Tweaks: Optimized audio resampling for better cross-platform performance.

Release 1.1.0: Major Audio Engine Update

• New Audio Engine: Overhauled the backend to support advanced echo suppression and better volume normalization.
• Virtual Driver Handling: Improved recognition of software-based audio mixers.
• Multi-Language Disclaimer Support: Each language now has a tailored disclaimer introduction.
• Expanded Compatibility: Added additional logic to support older devices without compromising performance.

Release 1.0.10: Echo Cancellation v3 & UI Polish

• Corrected Echo Cancellation Hyperparameters for Windows: Fine-tuned parameters for better suppression.
• Per-Language Disclaimers: Introduction messages now match the selected language.
• Minor UI Tweaks: Fixed alignment, error message stacking, and streamlined settings.

Release 1.0.7: Echo Cancellation v3

• Corrected Echo Cancellation Hyperparameters for Windows
• Updated Intro Disclaimers to Be Per-Language
• Small UI Changes‍

Release 1.0.6: Echo Cancellation v2, version control, and disclaimer

• We completely revamped our echo cancellation algorithms to improve the quality of background noise, audio feedback and error surpression. It will take a couple seconds to activate and adapt to your unique audio environment, but then it's smooth sailing from there!
• We also added a method to incentivize updating to the latest software version so that your app will have all bugs squashed
• Small bug fixes on UI (stacked boxes, ordering of error messages, simplified settings,etc)
• We added a disclaimer sound that will introduce the product at the beginning of a session

‍

‍

‍

These updates represent a steady, incremental improvement to both the audio engine and the user experience, culminating in a more stable, efficient, and user-friendly application. 🚀

‍

‍