QuickWhisper AI 4+

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.

* 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.

---

We'd love to hear them! Drop us a line at support@quickwhisper.app or add your suggestions to https://quickwhisper.featurebase.app/
Your support helps us make QuickWhisper better!