May 4th, 2026
QuickWhisper 1.28
We're excited to announce QuickWhisper 1.28, featuring a redesigned main interface, powerful organizational tools, expanded voice model options, and workflow enhancements!
New Features
Global Speakers List
Manage speakers consistently across all transcripts with reusable global speaker profiles. You can create speakers in Settings → Speakers. To add a global speaker to the transcript, just start typing their name.
Enhanced Speaker Diarization
Experience improved speaker detection with our new Sortformer model. It supports up to 4 speakers and provides better recovery from interruptions.
New on-device AI models
We've added 4 new AI models for summaries that you can download with one click of a button
Qwen 3.5 4B - Great for multilingual and structured summaries.
Llama 3.2 3B - Fastest and lightest for quick replies, simple rewrites.
Gemma 3 4B - Balanced speed and quality for quality summaries.
Gemma 3 12B - The most capable option for deeper reasoning, better writing quality, and more detailed answers. Requires more than 16Gb RAM.
Video Subtitle Export
Create videos with embedded/burned subtitles using our new export option (experimental)
Media Retention Policy
We've improved our transcoding logic and implemented a content retention policy to minimize disk usage for new recordings while maintaining quality.
As always, we're committed to refining QuickWhisper based on your feedback. These updates reflect our focus on creating a more intuitive, powerful, and flexible transcription experience.
QuickWhisper Team