Changelog
Follow new updates and improvements to QuickWhisper - lightning-fast and accurate transcriptions.
March 8th, 2025
New month brings you another feature-packed QuickWhisper release! Let’s have a look what we have for you today.
New Features
Fresh Look and Feel
QuickWhisper's start screen just got a stunning makeover! We've redesigned the interface with enhanced contrast and add distinctive personality, making it not just more visually appealing but also more functional.
Batch Transcription
Do you need to transcribe multiple files at once? Drag-n-drop files to QuickWhisper, select export format, and hit "Batch Transcribe." Files will be processed one by one. Each transcription remains individually accessible, allowing you to edit and manage them separately afterwards.
Speaker Diarization: 50% More Accurate!
We've made a breakthrough in our speaker diarization engine! This release delivers a remarkable 50% improvement in accuracy, placing QuickWhisper among the industry leaders in speaker diarization. It particularly shines in interview and podcast recording where speakers maintain clear time separation. The system now excels at:
More precise speaker change detection
Better handling of quick speaker transitions
Enhanced speaker consistency throughout long recordings
We'd love to hear about your experience with the improved diarization feature – share your feedback with us!
Ignore List
More control over transcription quality with our new Ignore List feature. This feature automatically filters non-verbal segments (like: [SILENCE], [MUSIC]), but also allows you to filter any undesired segments. You can access the feature in Settings → Ignore List or simply open context menu of a segments and click on "Delete and ignore in the future" to add it to the Ignore List.
Find & Replace
Tired of repeatedly correcting the same transcription errors? Our new Find & Replace feature is here to help! Create custom replacement rules to automatically correct repeating mistakes. Whether it's proper names, technical terms, or recurring phrases, set up your rules once and let QuickWhisper handle the rest. Perfect for maintaining consistency across all your transcriptions.
Note: This feature is currently in beta, and while powerful, results may occasionally vary from expected outcomes. We're actively collecting user feedback to improve its accuracy.
Audio Export
Take control of your audio recordings with our versatile new audio export options! Whether you need to export specific channel (microphone or system audio), or export the recording as a whole, we've got you covered. Perfect for anyone who needs more granular control over their meeting recordings.
History Search
Finding past transcripts has never been easier! Our new History Search feature lets you quickly locate specific transcripts by filename, date, or content. The smart search functionality supports both recent and archived transcriptions, making project organization effortless.
Got thoughts? We'd love to hear them! Drop us a line at support@quickwhisper.app or add your suggestions in the Feedback. Your support helps us make QuickWhisper better!
February 26th, 2025
We're excited to introduce QuickWhisper 1.7, bringing powerful project navigation, multi-track transcription mode, and huge performance optimisation!
New features
Transcription projects
Access your transcription projects with our revamped project structure. Your transcripts are now organised in an easy-to-navigate chronological list in the sidebar, making it simple to find and revisit transcription projects. You can also easily rename and delete projects via context menu.
Multi-track Mode (Podcast Mode)
Perfect for podcasts, interviews, and remote meetings where each speaker is recorded on a separate track! Simply import individual audio files from each participant, and QuickWhisper will combine them into a single, perfectly synchronized transcript.
For example, if you have separate recordings of the host and guest from your podcast, or individual tracks from each participant in your remote meeting, QuickWhisper will merge them while maintaining precise speaker attribution and timing.
Btw: When using Multi-track mode you can choose to align tracks by their end times instead of start times.
Removing Duplicated Segments
Say goodbye to duplicated segments! Our new filtering system automatically detects and removes repeated text segments in your transcripts. This is especially useful when transcribing lower-quality audio, where Whisper might produce duplicate segments like "Let's begin Let's begin Let's begin".
Note: While this feature works well for cleaning up transcription artifacts, use it carefully with content that intentionally contains repetition (like song lyrics, educational materials, or speeches with deliberate repetition for emphasis).
Paragraph Mode (BETA)
Get more natural, readable transcripts with the new Paragraph mode. Instead of breaking text into short segments, QuickWhisper will intelligently merge adjacent segments to form complete sentences or paragraphs. For example, rather than having three separate segments like "I wanted to", "tell you that", "the meeting is tomorrow", you'll get one natural segment: "I wanted to tell you that the meeting is tomorrow." This makes transcripts much easier to read and work with, especially when you don't need subtitle-style segmentation.
Note: Since this feature relies on Whisper's punctuation detection, it works best with clear audio.
System Audio Monitor
Recording system audio? Keep an eye on both audio sources with our new split volume meter. Now you can monitor Microphone and System audio levels separately in real-time, helping you catch and fix recording issues before they ruin your session. No more unpleasant surprises of discovering that your interview recording has only audio of your voice.
Transcription Progress Estimation
Know exactly when your transcription will be ready with our new time estimation feature. No more guessing, how much time to wait by looking at the progress circle. Especially comforting when working with longer transcriptions.
Quick Model and Language Selection
Model and language controls are now available from the main window. No need to go to the setting if you need to change these essential controls.
Performance
We've supercharged our transcription engine! Enjoy up to 20% faster processing times thanks to extensive low-level optimisations.
Got thoughts? We'd love to hear them! Drop us a line at support@quickwhisper.app or add your suggestions in the Feedback. Your support helps us make QuickWhisper better!
December 18th, 2024
🎄 As we wrap up 2024, we're excited to deliver one more release of QuickWhisper to make your transcription tasks in the new year smoother.
New features
Search Navigation
Finding specific content in your transcripts is now easier than ever. As you search, QuickWhisper not only shows you the total number of matches, but it allows you to navigate between these matches with Next and Previous buttons. You can also use common keyboard shortcuts to start search (Ctrl+F), and go to the next match (Cmd+G) or go back the the previous one (Cmd+Shift+G).
Filtering
You can now filter segments by Speaker or Labels, making it incredibly easy to navigate especially in long transcript. What's even better - when you use the Copy button with a filtered view, QuickWhisper only copies the visible segments.
Direct Printing
Getting your transcripts on paper is now just a click away. You can print transcripts directly from QuickWhisper by selecting File → Print or using the standard shortcut (Cmd+P). No need to export to a file first – just print and go.
Adjustable Font Size
We've also added adjustable font sizes to ensure comfortable reading for everyone. Use Cmd+ to increase the font size, Cmd- to decrease it, or quickly return to the default with Cmd+0.
Fixes
Fixed various minor UI inconsistencies
Enhanced overall performance and stability
Got thoughts? We'd love to hear them! Drop us a line at support@quickwhisper.app or add your suggestions in the Feedback section. Your thoughts and ideas helps us make QuickWhisper better!
Happy transcribing!
December 2nd, 2024
We're thrilled to present our most feature-packed update yet! This release brings professional-grade customisation, enhanced export options, and powerful new tools for managing your transcripts.
New features
Transcript search
Find exactly what you need - quickly locate specific words or phrases within the transcript
Manual speaker management
In addition to automatic speaker diarization, in 1.5 we bring manual controls for adding/removing speakers to transcripts. We’ve also added handy keyboard shortcuts so that you can assign speakers to segments blazing-fast.
Segment labels
Label segments that matter most for you goal. You select from: Decision, Action Item, Question, Highlight, Positive, Negative. These labels will be exported.
Merge segments
Perfect for cleaning up over-segmented transcripts - combine adjacent segments together for more useful results and better reading experience.
Adjustable timestamps
Fine-tune segment timing - manually adjust start and end times for perfect synchronization.
Start over recording
Lost your thought in the middle of a recording and need to start over? Hit the new Start Over button and begin fresh without leaving the recording window.
Advanced Settings
When dealing with complicated or low-quality recordings our new pre-processing option will be handy. While it may take a bit longer, transcriptions are usually getting better when you have multiple overlapping speakers, extended periods of silence, or background noise.
For power users who need precise control, we've exposed Whisper's advanced configuration options. Adjust decoding strategies, initial prompt, and entropy threshold to match your specific needs.
Note: The default settings work best for most cases - only adjust if you're familiar with Whisper's configuration.
We've also added revamped export to give you full control over your transcript's final shape:
New export formats
No you have more ways to share! We’ve added export to PDF, HTML, and Markdown.
Fixes
Fixed various minor UI inconsistencies
Enhanced overall performance and stability
Got thoughts? We'd love to hear them! Drop us a line at support@quickwhisper.app or add your suggestions in the Feedback section. Your feedback helps us make QuickWhisper better!
Happy transcribing!
November 4th, 2024
We're excited to bring you new features focused on making segments editing more efficient and lots of bugfixes!
New features
Hovering edit button
A convenient edit button appears when you hover any segment, helping you to switch to editing with fewer clicks.
Delete segments using keyboard
No more clicking around. Just select a segment and hit delete button to remove unwanted parts of your transcript.
Transcript View Controls
Compact View
See up to 3x more segments on screen without scrolling, making navigation in long transcripts much more convenient.
View both start and end times
See exactly when each segment starts and ends, essential for precise transcript timing. You can control timestamps view via Transcript menu in the system bar.
New Export Options
SBV subtitles
Export your transcripts directly in SBV format, compatible with YouTube and all major video platforms.
Fixes
Fixed various minor UI inconsistencies
Enhanced overall performance and stability
Got thoughts? We'd love to hear them! Drop us a line at support@quickwhisper.app or add your suggestions in the Feedback section. Your feedback helps us make QuickWhisper better!
Happy transcribing!
October 31st, 2024
We're incredibly excited to release our biggest update yet!
Introducing significant enhancements to audio management, transcript editing and speaker management. This update brings professional-grade features designed to streamline your transcription workflow.
New features
Smart Player
Ever wished you could hear exactly what you're reading in the transcript? Now you can! Our new smart audio makes you workflows easier:
Playback speed control
Watch segments highlighted in real-time as they're played
Navigate long transcript faster with visual segment previews
Advanced Transcript Editing
Take control of your transcripts with new editing capabilities:
Edit text in segments if you spot a a mistake.
Delete unwanted segments
Remove all segments before/after current position with one click to trim the fat from your transcripts
Perfect for cleaning up meeting recordings
Better Speaker Management
Remember our experimental Speaker detection feature? We've taken it to the next level.
Change speakers name from generic Speaker 1, Speaker 2 to real ones.
Manually assigning speakers to segments to correct auto-detection errors.
Enhanced Recording Controls
Choose to record system audio exclusively, eliminating microphone feedback when not using headphones.
New High-Performing Voice Model
Added the latest OpenAi’s Large v3 Turbo. The new model has transcription quality of Large v2 and lightning-fast speed close to Base models on benchmarks. You should give it a try!
Optimised Size
We sent QuickWhisper to the gym (metaphorically). After optimisations the app lost more than 100Mb, which means higher perfromance and faster updates.
Fixes
Because nobody likes bugs:
Fixed Large v2 Norwegian model download issues
Corrected speaker detection progress indicator showing over 100%
Resolved empty transcription screen after cancellation
Got thoughts? We'd love to hear them! Drop us a line at support@quickwhisper.app or add you suggestions in the Feedback section. Your feedback helps us make QuickWhisper better!
Happy transcribing!
September 12th, 2024
In this long-waited release we introduce Speaker diarization, a feature that will elevate your transcription experience by a mile.
New Features
Speaker Detection (Beta)
Automatically identify and separate different speakers in your recordings. Speaker detection can be done via a new button in the transcript view.
⚠️ Please note that this process is computationally intensive and may take some time. We're eager to hear your feedback on this initial release!
Language-specific Voice Models
We've added specialised models for 🇫🇷 French, 🇯🇵 Japanese, 🇮🇱 Hebrew, and 🇳🇴 Norwegian, offering improved accuracy and lower error rates compared to standard multi-lingual versions.
Improvements
Enhanced Language Selection
Our redesigned language selector now features flags for each language, making it easier and faster to find the right language for your transcription.
Right-to-Left (RTL) languages support
Automatic RTL view switching for Hebrew and Arabic languages, enhancing readability and user experience.
Empty state
If for any reason QuickWhisper couldn't transcribe the source it will show a message clearly explaining the reason.
August 28th, 2024
New release brings a lot of new features and improvements to enhance your transcription experience. Here’s what’s new:
New Features
System Audio Recording: Record audio directly from other applications on your Mac, making it easier to capture and transcribe calls and meetings. You can record any calls in Zoom, MS Teams, Google Meet, Webex, WhatsUp, Discord, Telegram, etc.
⚠️ For the best transcription quality we recommend use of headphones to isolate audio from your microphone and other speakers.
Chrome and Firefox Extensions: We released browser extensions for Google Chrome and Firefox to help you copy URLs to QuickWhisper with a single click.
New Language Selector:With our new language selector you can find the right language faster.
Speaker Information in Subtitles and Segments: If you record System Audio, your transcription will contain information which words are yours and which belong to another speaker. Speaker information will also be added to export of segments and subtitles.
Favicons: When pasting URLs into QuickWhisper, website favicons are now displayed.
Fixes
External Microphone Support: Resolved issues affecting the use of external microphones for recording.
Dark Mode Enhancements: Adjustments to UI elements in Dark Mode for better visibility and a more consistent user experience.
Transcription Flexibility: Ability to stop an ongoing transcription to switch Voice Model or Languages on the go.
July 15th, 2024
This release is packed with features:
Fast and Secure Transcriptions Anywhere: You can quickly and accurately transcribe audio and video files without an internet connection. The whole process runs locally on your machine ensuring your privacy is protected.
Expanded Formats Compatibility: Support of a wide range of audio and video file formats, including WAV, MKV, AVI, MP3, M4A, M4V, MOV, MP4, and CAF.
Direct URL Transcriptions: Easily transcribe media from URLs, including online videos from YouTube and Vimeo, files from Google Drive and Dropbox, and other platforms.
Built-in Voice Recording: Record audio directly within the app with our new built-in functionality.
Quality Selection: Choose the Voice Model that best fits your needs to get the perfect balance of speed and accuracy.
Export Flexibility: Export your transcriptions in various formats such as TXT, CSV, JSON, SRT, and VTT.
Save Projects: Save your transcription projects for future reference or share them with colleagues and friends.
Drag & Drop: Drag and Drop files directly into QuickWhisper to start the transcription.
Support for Voice Memos: Seamlessly transcribe your recordings from the Voice Memos app. Just drag and drop your voice memos to the app to get a transcription.
Transcribe iMessage Audio Messages: Easily convert audio messages from iMessage into text.
Flexible Viewing Options: Choose to view your transcriptions as full text for a comprehensive read or in segments for focused analysis.
Reading Mode: Enjoy a clearer and more readable transcription output with each sentence shown on a separate line, making it easier to review your transcript.
Configurable Working Folder: You can set a default working folder for saving recordings and transcription results. Organize your files exactly how you want them.