buzz
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
File Explorer
Download Latest Version (.zip)- ci.yml
- gh-pages.yml
- manual-build.yml
- snapcraft.yml
- pytest.run.xml
- launch.json
- settings.json
- tasks.json
- build-appimage.sh
- color-background.svg
- fullscreen.svg
- gui-text-color.svg
- new-window.svg
- add_FILL0_wght700_GRAD0_opsz48.svg
- buzz-banner.jpg
- buzz-icon-1024.png
- Buzz.exe.local
- buzz.icns
- buzz.ico
- buzz.png
- buzz.svg
- cancel_FILL0_wght700_GRAD0_opsz48.svg
- delete_FILL0_wght700_GRAD0_opsz48.svg
- file_download_black_24dp.svg
- info-circle.svg
- mic_FILL0_wght700_GRAD0_opsz48.svg
- open_in_full_FILL0_wght700_GRAD0_opsz48.svg
- pause_black_24dp.svg
- play_arrow_black_24dp.svg
- redo_FILL0_wght700_GRAD0_opsz48.svg
- resize_black.svg
- speaker-identification.svg
- translate_black.svg
- undo_FILL0_wght700_GRAD0_opsz48.svg
- update_FILL0_wght700_GRAD0_opsz48.svg
- url.svg
- visibility_FILL0_wght700_GRAD0_opsz48.svg
- visibility_off_FILL0_wght700_GRAD0_opsz48.svg
- __init__.py
- dao.py
- transcription_dao.py
- transcription_segment_dao.py
- __init__.py
- entity.py
- transcription.py
- transcription_segment.py
- __init__.py
- transcription_service.py
- __init__.py
- db.py
- helpers.py
- migrator.py
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- buzz.po
- ca_ES.json
- da_DK.json
- de_DE.json
- es_ES.json
- it_IT.json
- ja_JP.json
- lv_LV.json
- nl.json
- pl_PL.json
- pt_BR.json
- ru.json
- uk_UA.json
- zh_CN.json
- zh_TW.json
- __init__.py
- plugin.py
- ca_ES.json
- da_DK.json
- de_DE.json
- es_ES.json
- it_IT.json
- ja_JP.json
- lv_LV.json
- nl.json
- pl_PL.json
- pt_BR.json
- ru.json
- uk_UA.json
- zh_CN.json
- zh_TW.json
- __init__.py
- plugin.py
- ca_ES.json
- da_DK.json
- de_DE.json
- es_ES.json
- it_IT.json
- ja_JP.json
- lv_LV.json
- nl.json
- pl_PL.json
- pt_BR.json
- ru.json
- uk_UA.json
- zh_CN.json
- zh_TW.json
- __init__.py
- plugin.py
- ca_ES.json
- da_DK.json
- de_DE.json
- es_ES.json
- it_IT.json
- ja_JP.json
- lv_LV.json
- nl.json
- pl_PL.json
- pt_BR.json
- ru.json
- uk_UA.json
- zh_CN.json
- zh_TW.json
- __init__.py
- plugin.py
- ca_ES.json
- da_DK.json
- de_DE.json
- es_ES.json
- it_IT.json
- ja_JP.json
- lv_LV.json
- nl.json
- pl_PL.json
- pt_BR.json
- ru.json
- uk_UA.json
- zh_CN.json
- zh_TW.json
- __init__.py
- plugin.py
- ca_ES.json
- da_DK.json
- de_DE.json
- es_ES.json
- it_IT.json
- ja_JP.json
- lv_LV.json
- nl.json
- pl_PL.json
- pt_BR.json
- ru.json
- uk_UA.json
- zh_CN.json
- zh_TW.json
- __init__.py
- plugin.py
- __init__.py
- AGENTS.md
- base.py
- CLAUDE.md
- loader.py
- manager.py
- post_processing.py
- __init__.py
- recording_transcriber_mode.py
- settings.py
- shortcut.py
- shortcuts.py
- __init__.py
- keyring_store.py
- __init__.py
- file_transcriber.py
- local_whisper_cpp_server_transcriber.py
- openai_whisper_api_file_transcriber.py
- recording_transcriber.py
- transcriber.py
- whisper_cpp.py
- whisper_file_transcriber.py
- __init__.py
- plugin_settings_dialog.py
- plugins_dialog.py
- __init__.py
- file_transcription_preferences.py
- folder_watch_preferences.py
- preferences.py
- __init__.py
- folder_watch_preferences_widget.py
- general_preferences_widget.py
- models_preferences_widget.py
- preferences_dialog.py
- shortcuts_editor_preferences_widget.py
- __init__.py
- advanced_settings_button.py
- advanced_settings_dialog.py
- file_transcriber_widget.py
- file_transcription_form_widget.py
- hugging_face_search_line_edit.py
- initial_prompt_text_edit.py
- languages_combo_box.py
- mms_language_line_edit.py
- tasks_combo_box.py
- transcription_options_group_box.py
- __init__.py
- export_transcription_menu.py
- speaker_identification_widget.py
- transcription_resizer_widget.py
- transcription_segments_editor_widget.py
- transcription_view_mode_tool_button.py
- transcription_viewer_widget.py
- __init__.py
- about_dialog.py
- application.py
- audio_devices_combo_box.py
- audio_meter_widget.py
- audio_player.py
- form_label.py
- icon.py
- icon_presentation.py
- import_url_dialog.py
- line_edit.py
- main_window.py
- main_window_toolbar.py
- menu_bar.py
- model_download_progress_dialog.py
- model_type_combo_box.py
- openai_api_key_line_edit.py
- password_line_edit.py
- presentation_window.py
- record_button.py
- record_delegate.py
- recording_transcriber_widget.py
- sequence_edit.py
- text_display_box.py
- toolbar.py
- transcription_record.py
- transcription_task_folder_watcher.py
- transcription_tasks_table_widget.py
- update_dialog.py
- video_player.py
- __init__.py
- __main__.py
- __version__.py
- action.py
- assets.py
- buzz.py
- cache.py
- cli.py
- conn.py
- cuda_setup.py
- dialogs.py
- ffmpeg_video_player.py
- file_transcriber_queue_worker.py
- locale.py
- model_loader.py
- paths.py
- pip_utils.py
- recording.py
- schema.sql
- sounddevice_player.py
- transformers_whisper.py
- translator.py
- update_checker.py
- whisper_audio.py
- SDL2.dll
- 1_file_import.md
- 2_live_recording.md
- 3_translations.md
- 4_edit_and_resize.md
- 5_speaker_identification.md
- 6_transcription_viewer.md
- 7_plugins.md
- _category_.yml
- cli.md
- faq.md
- index.md
- installation.md
- preferences.md
- 1_file_import.md
- 2_live_recording.md
- 3_translations.md
- 4_edit_and_resize.md
- _category_.yml
- cli.md
- faq.md
- index.md
- installation.md
- preferences.md
- custom.css
- index.module.css
- index.tsx
- banner.jpg
- favicon.ico
- latest-development-build.jpeg
- .nojekyll
- .gitignore
- babel.config.js
- docusaurus.config.js
- package-lock.json
- package.json
- README.md
- sidebars.js
- tsconfig.json
- run-buzz.sh
- ctc_forced_aligner_windows_mutex.patch
- README.zh_CN.md
- build_ctc_forced_aligner.py
- download-models.py
- io.github.chidiwilliams.Buzz.svg
- io.github.chidiwilliams.Buzz.metainfo.xml
- buzz-1-import.png
- buzz-2-main_screen.png
- buzz-3-preferences.png
- buzz-3.2-model-preferences.png
- buzz-4-transcript.png
- buzz-5-live_recording.png
- buzz-6-resize.png
- snapcraft.yaml
- audio-long.mp3
- ggml-tiny.bin
- whisper-french.mp3
- whisper-latvian.wav
- transcription_dao_test.py
- transcription_test.py
- transcription_service_test.py
- __init__.py
- loader_test.py
- plugin_system_test.py
- settings_test.py
- __init__.py
- keyring_store_test.py
- __init__.py
- file_transcriber_queue_worker_test.py
- openai_whisper_api_file_transcriber_test.py
- recording_transcriber_test.py
- transcriber_test.py
- transformers_whisper_test.py
- whisper_cpp_test.py
- whisper_file_transcriber_test.py
- plugin_settings_dialog_test.py
- plugins_dialog_test.py
- __init__.py
- folder_watch_preferences_widget_test.py
- general_preferences_widget_test.py
- models_preferences_widget_test.py
- preferences_dialog_test.py
- __init__.py
- transcription_resizer_widget_test.py
- transcription_segments_editor_widget_test.py
- transcription_viewer_widget_additional_test.py
- __init__.py
- advanced_settings_dialog_test.py
- audio_meter_widget_test.py
- audio_player_test.py
- conftest.py
- export_transcription_menu_test.py
- file_transcriber_widget_test.py
- hugging_face_search_line_edit_test.py
- import_url_dialog_test.py
- main_window_test.py
- menu_bar_test.py
- model_download_progress_dialog.py
- model_type_combo_box_test.py
- openai_api_key_line_edit_test.py
- password_line_edit_test.py
- presentation_window_test.py
- recording_transcriber_widget_test.py
- shortcuts_editor_widget_test.py
- speaker_identification_widget_test.py
- transcription_task_folder_watcher_test.py
- transcription_tasks_table_widget_test.py
- transcription_viewer_test.py
- update_dialog_test.py
- video_player_test.py
- __init__.py
- app_main.py
- audio.py
- cache_test.py
- cli_test.py
- conftest.py
- ffmpeg_video_player_test.py
- gui_test.py
- mock_qt.py
- mock_sounddevice.py
- model_loader.py
- model_loader_test.py
- pip_utils_test.py
- recording_test.py
- recording_transcriber_test.py
- sounddevice_player_test.py
- speaker_identification_e2e_test.py
- transformers_transcriber_test.py
- translator_test.py
- update_checker_test.py
- .coveragerc
- .gitignore
- .gitmodules
- .pre-commit-config.yaml
- .pylintrc
- .python-version
- AGENTS.md
- Buzz.desktop
- Buzz.spec
- CLAUDE.md
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- ctc_forced_aligner
- deepmultilingualpunctuation
- demucs_repo
- entitlements.plist
- hatch_build.py
- installer.iss
- LICENSE
- main.py
- Makefile
- msgfmt.py
- pyproject.toml
- pytest.ini
- README.ja_JP.md
- README.md
- uv.lock
- whisper.cpp
- whisper_diarization
# Installation Guide
git clone https://github.com/chidiwilliams/buzz
Downloads the entire project code from GitHub to your computer.
cd buzz
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- APT (Debian/Ubuntu ๊ณ์ด) Built into Debian/Ubuntu-based Linux distributions.
- Python 3 Python is required to use pip.
sudo apt-get install libportaudio2 libcanberra-gtk-module libcanberra-gtk3-module
Installs directly from the APT package repository (Debian/Ubuntu-based).
pip install buzz-captions
Installs the package published on PyPI directly โ no need to clone the source.
pip3 install -U torch==2.8.0+cu129 torchaudio==2.8.0+cu129 --index-url https://download.pytorch.org/whl/cu129
Installs the package published on PyPI directly โ no need to clone the source.
pip3 install nvidia-cublas-cu12==12.9.1.4 nvidia-cuda-cupti-cu12==12.9.79 nvidia-cuda-runtime-cu12==12.9.79 --extra-index-url https://pypi.ngc.nvidia.com
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install buzz-captions
Installs the package published on PyPI directly โ no need to clone the source.
python -m buzz
Runs the Python script (or module).
pip3 install -U torch==2.8.0+cu129 torchaudio==2.8.0+cu129 --index-url https://download.pytorch.org/whl/cu129
Installs the package published on PyPI directly โ no need to clone the source.
pip3 install nvidia-cublas-cu12==12.9.1.4 nvidia-cuda-cupti-cu12==12.9.79 nvidia-cuda-runtime-cu12==12.9.79 --extra-index-url https://pypi.ngc.nvidia.com
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.
4. Make
Medium- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make
Compiles the code based on the generated build configuration to produce an executable.
