LIVE
Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|OpenAI models are coming to Google Cloud21/10/26 · OpenAI|OpenAI details ChatGPT's new advertising infrastructure21/10/26 · OpenAI|Liquid AI unveils LFM3, a base for specialized multimodal models27/10/26 · Liquid AI|US Police Departments Use AI to Flag 'Suspicious' Driving Behavior27/10/26|AllenAI questions whether LLMs can judge research novelty27/10/26 · AllenAI|Open-Source AI Tools Aim to Speed Up Dementia Research27/10/26 · NVIDIA|Solid-state transformers eyed as a fix for AI's power grid bottleneck27/10/26|OpenAI expands Oracle partnership to bring business apps into ChatGPT27/10/26 · OpenAI|OpenAI publishes a page announcing 'GPT-6.1 Terra', with no technical details available26/10/26 · OpenAI|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|OpenAI models are coming to Google Cloud21/10/26 · OpenAI|OpenAI details ChatGPT's new advertising infrastructure21/10/26 · OpenAI|Liquid AI unveils LFM3, a base for specialized multimodal models27/10/26 · Liquid AI|US Police Departments Use AI to Flag 'Suspicious' Driving Behavior27/10/26|AllenAI questions whether LLMs can judge research novelty27/10/26 · AllenAI|Open-Source AI Tools Aim to Speed Up Dementia Research27/10/26 · NVIDIA|Solid-state transformers eyed as a fix for AI's power grid bottleneck27/10/26|OpenAI expands Oracle partnership to bring business apps into ChatGPT27/10/26 · OpenAI|OpenAI publishes a page announcing 'GPT-6.1 Terra', with no technical details available26/10/26 · OpenAI|
AppRisingofficial publisher

Buzz (Whisper)

App : A product you use directly

Local transcription with Whisper, SRT and VTT export, no account or cloud required.

Free and private transcription for everyone.

Overall score
9.1 /10
Security: nothing to flag
Utility
8.0
Reliability
10.0
Security
No caveat on record
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Recording a meeting, a conference or a video and getting an accurate transcript usually means going through an online service that stores your audio files on its servers. Buzz solves this problem by running the Whisper speech recognition engine directly on your computer, without sending any data outside.

In practice, you import an audio or video file, or paste a YouTube link, and Buzz starts the transcription locally. You can also enable real-time transcription from your microphone, with a presentation window suited for public events. Once done, you export the result as TXT, SRT or VTT depending on your needs.

Buzz is aimed at journalists, researchers, content creators, subtitlers and anyone who regularly processes audio or video and wants to keep control of their data. The tool also suits privacy-conscious users who refuse to entrust their recordings to a third party.

That said, Buzz requires a minimum of technical comfort to install, especially on Windows where the application is unsigned and triggers a security warning. Users looking for a fully browser-based, install-free solution will need to look elsewhere.

What it offers

  • ·Offline transcription of audio and video files as well as YouTube links, with no internet connection required.
  • ·Real-time transcription from the microphone, with a dedicated presentation window for events and conferences.
  • ·Speech separation before transcription to improve accuracy on noisy recordings.
  • ·Speaker identification in transcribed media.
  • ·GPU acceleration via CUDA for Nvidia cards, Apple Silicon for M1 and later Macs, and Vulkan for most other GPUs.
  • ·Export of transcripts as TXT, SRT and VTT.
  • ·Advanced transcript viewer with search, playback controls and speed adjustment.
  • ·Watch folder for automatic transcription of new files, and a command-line interface for automation.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
windows, macos, linux
Licence
MIT
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active
Last release
23 August 2026

Links and repository checked on 25 October 2026 · added on 1 October 2022

How to install Buzz (Whisper)

1. Go to SourceForge (https://sourceforge.net/projects/buzz-captions/files/) to download the installer for your system (macOS: .dmg, Windows: installer, Linux: Flatpak, Snap or AppImage). 2. On Windows, if a security warning appears, click "More info" then "Run anyway": the application is unsigned but its source code is public and auditable on GitHub. 3. On Linux, you can also install via Flatpak by running: flatpak install flathub io.github.chidiwilliams.Buzz 4. Launch Buzz, import an audio or video file (or paste a YouTube link) and choose the Whisper model suited to your machine. 5. If you have an Nvidia card, go to Help > About Buzz to install CUDA acceleration and speed up transcriptions.
flatpak install flathub io.github.chidiwilliams.Buzz

Recipes using Buzz (Whisper)

In the same category

Whole category Audio, voice & music →