Bug fixes and minor improvements.

• Fixed Youtube link downloading
• Added option to import folder
• Extra settings for live recordings
• Adjusted live recording batching process to avoid min-word cuts
• Update checker for Windows and Macs
• Added voice activity detection to whisper.cpp

Windows and macOS installation files for the release are available on SourceForge

Buzz for Linux you can get on Flathub and Snap

Note for Windows

To install Buzz from the releases section below, download all three Windows files (one *.exe and both *.bin files) and run the *.exe
App is not signed, you will get a warning when you install it. Select More info -> Run anyway.

Fixed support for whisper.cpp on older CPUs and issues in speaker identification.

Windows and macOS installation files for the release are available on SourceForge

Buzz for Linux you can get on Flathub and Snap

Note for Windows

To install Buzz from the releases section below, download all three Windows files (one *.exe and both *.bin files) and run the *.exe
App is not signed, you will get a warning when you install it. Select More info -> Run anyway.

Fixes for Flatpak builds for the previous release of 1.4.1

Windows and macOS installation files for the release are available on SourceForge

Buzz for Linux you can get on Flathub and Snap

Adding speaker identification on transcriptions and video support for transcription viewer, improvements to transcription table and support for over 1000 of worlds languages via MMS models as well as separate window to show live transcripts on a projector.

Release details:

• Speaker identification on finished transcripts
• Support for video in transcription viewer
• Presentation (projector) window for live transcripts
• Ability to add notes and restart transcriptions in main table
• Adding support for more than 1000 languages via MMS model family when transcribing with Huggingface transcription type
• Adding support for PEFT models when transcribing with Huggingface transcription type
• Adding support for 8bit quantization for Huggingface and faster Whisper transcriptions
• Updated libraries and dependencies to support latest GPUs
• Support for secrets portal for snap packages on Linux
• Ability to specify model to use when transcribing with OpenAI API
• Ability to access application logs from About screen

Windows and macOS installation files for the release are available on SourceForge

Buzz for Linux you can get on Flathub and Snap

This release fixes wheel build issues from previous release 1.3.2.

Windows and macOS installation files for the release are available on SourceForge

Buzz for Linux you can get on Flathub and Snap

This release introduces Vulkan GPU support for whisper.cpp making it significantly faster even on laptops. Real-time transcription is possible even with large models on computers with ~5GB RAM video cards. There is now an option to separate voice tracks before the audio is transcribed. This can improve transcript accuracy for audios with background noises or music. Faster whisper was updated to the latest version adding noticeable speed improvement.

Additional improvements

• Option to switch the UI language from preferences
• Library updates for better Linux compatibility, especially in Flatpak installations
• Option to upload live transcripts to a server. See BUZZ_UPLOAD_URL
• Search and additional controls in Transcription viewer by @shlomi-dr
• Added UI translation for German, Dutch, Danish and Portuguese (Brazilian)
• Minor bug fixes

New Contributors

• @oleguldberg made their first contribution in #1045
• @Ironship made their first contribution in #1120
• @Vistaus made their first contribution in #1123
• @Elandrya2711 made their first contribution in #1156
• @GoldMath made their first contribution in #1158
• @ericdq made their first contribution in #1168
• @prschopf made their first contribution in #1190
• @shlomi-dr made their first contribution in #1224
• @greatdaveo made their first contribution in #1246

Full Changelog: v1.2.0...v1.3.2

What's Changed

• Will add Mac arch to release file names by @raivisdejus in #905
• Add Japanese translation by @nunawa in #909
• Update translations by @raivisdejus in #911
• Fix for exporting just resized segments by @raivisdejus in #912
• Adding word level timestamps to CLI by @raivisdejus in #913
• Updated local GPU notes by @raivisdejus in #914
• Adding setting for favorite languages by @raivisdejus in #915
• Adding note on dll backup for windows by @raivisdejus in #916
• Adding note installation for Macs by @raivisdejus in #917
• Adding translation for ok/cancel buttons by @raivisdejus in #918
• Adding note on Windows warning by @raivisdejus in #919
• Will build Windows with GPU support by @raivisdejus in #920
• Adding support for dark themed OSes by @raivisdejus in #926
• Will set custom dark mode only on windows by @raivisdejus in #927
• Will remember column visibility and add context menu to table header by @raivisdejus in #929
• Fix for dark theme on Windows 11 by @raivisdejus in #930
• Fallback for queued_at having no value by @raivisdejus in #932
• Live recording sliding window by @raivisdejus in #933
• Fix for url import dialog by @raivisdejus in #937
• Adding logging to url download case by @raivisdejus in #938
• Removing post processing on uls downloads by @raivisdejus in #941
• Fix for safetensor model detection by @raivisdejus in #943
• Adding path to ffmpeg for installed app on windows by @raivisdejus in #942
• Will not check process return code, but error by @raivisdejus in #945
• Fix for changing font for Windows dark mode by @raivisdejus in #947
• Adding warning on possibly invalid API key by @raivisdejus in #950
• Adding cudnn to LD_LIBRARY_PATH for snap by @raivisdejus in #951
• Adding support for Turbo model by @raivisdejus in #953
• Mitigation for incomplete downloads by @raivisdejus in #958
• Adding note on offline usage by @raivisdejus in #959
• Fix for row height on long transcriptions with a lot of rows by @raivisdejus in #960
• Adding notes to FAQ by @raivisdejus in #962
• Fix for url imports by @raivisdejus in #965
• Update buzz.po by @Chenghao999 in #966
• Adding turbo models by @raivisdejus in #967
• Fix for column visibility on Macs by @raivisdejus in #969
• Update README.md by @mriamnobody in #970
• Adding word level timestamps for Huggingface (transformers) whisper by @raivisdejus in #971
• Update buzz.po by @albanobattistella in #977
• Update buzz.po by @Chenghao999 in #973
• Adding Core ML support for WhisperCpp by @raivisdejus in #976
• Cn language support by @Chenghao999 in #982
• Adding locale override by @raivisdejus in #985
• Adding option to copy transcription source from transcription table by @raivisdejus in #986
• Adding support for cookiefile for Youtube downloads by @raivisdejus in #988
• Fix for disabled folder watch running on startup by @raivisdejus in #994
• Will close the app on task finish in CLI by @raivisdejus in #995
• Adding option to hide GUI window in CLI mode by @raivisdejus in #996
• Will not run app during the build by @raivisdejus in #1002
• Adding option to import urls via CLI by @raivisdejus in #1003

New Contributors

• @nunawa made their first contribution in #909
• @Chenghao999 made their first contribution in #966
• @mriamnobody made their first contribution in #970

Full Changelog: v1.1.0...v1.2.0

What's Changed

• Fix for language detection by @raivisdejus in #844
• Add Ukrainian translation by @xalt7x in #846
• Fix for build failing to generate translation mo by @raivisdejus in #847
• Adding cibuildwheels to build wheels by @raivisdejus in #842
• Fix for finnish huggingface model download by @raivisdejus in #864
• 862 fix for multi part model lownload by @raivisdejus in #865
• Will remove win32 dlls by @raivisdejus in #867
• Will disable CUDA for faster whisper on Windows to prevent error by @raivisdejus in #868
• Will restore "Run" button on progress cancellation by @raivisdejus in #869
• Will print progress while processing with Huggingface by @raivisdejus in #870
• Will prevent duplicate tasks in folder watch by @raivisdejus in #871
• Add documantation by @raivisdejus in #872
• Adding note on PaErrorCode-9999 by @raivisdejus in #874
• Adding note on CUDA 12 for Faster whisper by @raivisdejus in #875
• Fix for macOS 13 test by @raivisdejus in #876
• Will revert to using windows dll from backup by @raivisdejus in #880
• Adding note on ffmpeg + fix for faster whisper on macOS by @raivisdejus in #882
• Will build universal binary on macOS by @raivisdejus in #881
• Adding note on running buzz from source on macos by @raivisdejus in #885
• Adding note on running buzz from source on macos by @raivisdejus in #886
• Adding ability to resize subtitles by @raivisdejus in #888
• Will combine sentences into paragraphs when exporting txt by @raivisdejus in #889
• Fix for extra spaces in whisper.cpp transcripts by @raivisdejus in #890
• Fix for duplicate segments in whisper.cpp by @raivisdejus in #891
• Adding option to set n_threads for Whisper.cpp by @raivisdejus in #892
• Adding option to specify different API for translation by @raivisdejus in #893
• Adding option to specify custom model root by @raivisdejus in #894
• Create CODE_OF_CONDUCT.md by @Lucyeoh in #896
• Upgrade to 1.1.0 by @chidiwilliams in #900

New Contributors

• @xalt7x made their first contribution in #846
• @Lucyeoh made their first contribution in #896

Full Changelog: v1.0.1...v1.1.0

What's Changed

• Fixes snap localizations by @raivisdejus in #829
• Fixed typo by @raivisdejus in #831
• Adding support for alternate faster whisper model name by @raivisdejus in #832
• Will ensure snaps have localizations by @raivisdejus in #835
• Fix for whisper.dll by @raivisdejus in #834
• Will ensure snaps have localizations by @raivisdejus in #837
• Will build wheels in actions for testing by @raivisdejus in #838
• Fix for API key check by @raivisdejus in #841

Full Changelog: v1.0.0...v1.0.1

What's Changed

• feat: enable prompt option for Whisper.cpp and OpenAI API by @chidiwilliams in #706
• New Polish translation by @Sebek05 in #721
• Will remember previously used used huggingface model by @raivisdejus in #736
• Adding fix for multi-byte segments in whisper.cpp by @raivisdejus in #734
• Will make default app screen fit all columns by @raivisdejus in #744
• Will check if model from settings is supported for live transctiption by @raivisdejus in #740
• Will add more media formats by @raivisdejus in #750
• Fix for localizations, adding Latvian translatiosn by @raivisdejus in #752
• Test improvements by @raivisdejus in #755
• Adding missing translation by @raivisdejus in #756
• Limit Huggingface model download size by @raivisdejus in #754
• Will add huggingface model id to the transcription table by @raivisdejus in #758
• Will allow window to be resized smaller. by @raivisdejus in #762
• Adding option to delete settings on uninstall by @raivisdejus in #765
• Fixing snap build by @raivisdejus in #767
• Updating github actions by @raivisdejus in #768
• Fixing preference checkboxes by @raivisdejus in #769
• Adding notes on system audio on Windows and Linux by @raivisdejus in #771
• Adding GPU support for Huggingface models by @raivisdejus in #772
• Updating codecov to v4 by @raivisdejus in #770
• Test build for GPU snap by @raivisdejus in #773
• Will download HF models to Buzz cache folder by @raivisdejus in #775
• Fixed link by @raivisdejus in #777
• Fix for HF downlaod progress in SNAPs by @raivisdejus in #779
• Add live transcript export by @raivisdejus in #784
• Adding setting for custom OpenAI base url by @raivisdejus in #785
• Fix for record button being "record" and not "stop" when model downlo… by @raivisdejus in #786
• Fix for live transcription with Faster whisper by @raivisdejus in #787
• Fix for not remembering word level timings in folder watch preferences by @raivisdejus in #789
• Will re-enable audio player on Linux by @raivisdejus in #793
• Fix for snap audio playback by @raivisdejus in #795
• Add llm translations by @raivisdejus in #791
• Adding translation usage instructions by @raivisdejus in #798
• Updating for compatability with Ubuntu 24.04 by @raivisdejus in #799
• Fix for API key validation by @raivisdejus in #802
• 801 add large v2 v3 models by @raivisdejus in #803
• Fix for macOS actions cache by @raivisdejus in #804
• Adding translations to tasks and ok/cancel buttons by @raivisdejus in #805
• Fix for locales in *.whl and snaps by @raivisdejus in #806
• Adding support for Whisper API in live recordings by @raivisdejus in #807
• Switch whisper model cache to /models/ by @raivisdejus in #808
• Adding CUDA / GPU support to whisper model by @raivisdejus in #809
• Adding translation for Yes/No buttons by @raivisdejus in #811
• Fix for default HF model by @raivisdejus in #812
• Adding support for Groq.com API by @raivisdejus in #813
• Switching to pipeline for HF whisper by @raivisdejus in #814
• Fix for large v3 faster whisper model by @raivisdejus in #815
• Will filter out junk whisper adds on silence by @raivisdejus in #816
• Adding custom model size for Whisper.cpp and Faster Whisper by @raivisdejus in #820
• Adding translations by @raivisdejus in #821
• Adding ability to change application font size by @raivisdejus in #822

New Contributors

• @raivisdejus made their first contribution in #736

Full Changelog: v0.9.0...v1.0.0