Buzz transcription with the Buzz Whisper app

by Chidi Williams

Buzz is a free desktop app that runs Whisper on your computer. Skip the install: WhipScribe transcribes it in your browser. Packs: $4 for 500 minutes, $12 for 2,000, $24 for 5,000; Workspace $19 a month. Up to 10 hours or 5 GB per file. Measured turnaround: about 2 minutes per audio hour. 99 languages. Checked 25 Oct 2026.

Don’t want to install Buzz? Drop the file here.

Every recording starts with a free preview of its opening minutes. Credits never expire.

Here is what Buzz does, where it struggles, and what to use when you would rather not run it yourself.

macOS, Linux, Windows · free

Buzz on your computer, or upload the file to WhipScribe

	Buzz	WhipScribe
Install	Desktop app: .dmg (Mac) and .exe (Windows) from SourceForge, Flatpak or Snap on Linux, or pip install buzz-captions on Python 3.12; the Windows build is unsigned, so Windows warns on install¹	Nothing to install: upload the file in a browser. Transcribed on our own servers.
Platforms	macOS on Apple silicon (1.4.5 is the last version for Intel Macs), Windows, Linux¹²	Web, API, MCP
Speakers	Speaker identification in transcribed media, listed as a feature¹	Named in the summary, key quotes and chapters
Languages	More than 90 languages, through Whisper³	99+, detected automatically
Export formats	TXT, SRT and VTT¹	TXT, DOCX, SRT, VTT, JSON
Price	Free and open source (MIT licence)¹	A free preview of the opening minutes, then $4 for 500 minutes, $12 for 2,000 minutes, $24 for 5,000 minutes; Workspace $19 a month. Credits never expire.

Buzz column: the project’s own pages, numbered in the table.

chidiwilliams/buzz · README (GitHub), fetched 26 Oct 2026
chidiwilliams/buzz · releases (v1.4.5, 23 Aug 2026), fetched 26 Oct 2026
buzzcaptions.com · Buzz Classic and Buzz on macOS, fetched 26 Oct 2026

WhipScribe column: pricing and measured turnaround.

Buzz Whisper, Buzz Classic and Buzz Captions: which is which

Three names point at two apps by the same developer, Chidi Williams. "Buzz Whisper" is not a separate product: it is the free Buzz app, named for the OpenAI Whisper models it runs.

Latest release: v1.4.5, published 23 Aug 2026, with Mac builds for Apple silicon and Intel, a Windows installer and a Linux wheel. The README says Buzz now requires Apple silicon and that 1.4.5 is the last version for Intel Macs.

buzzcaptions.com still describes Buzz Classic for macOS as Intel; the README, updated more recently, is the one to follow.

Buzz runs on your own computer, so speed depends on your machine and the model size you pick. If you would rather not install anything, upload the file above: the transcript comes back in your browser.

Name you searched	What it is	Where to get it	Price
Buzz, Buzz Whisper, chidiwilliams/buzz	The open-source desktop app on GitHub. Runs Whisper, Whisper.cpp, Faster Whisper, Whisper-compatible Hugging Face models and the OpenAI Whisper API.	SourceForge (Mac, Windows), Flathub or Snap (Linux), PyPI	Free, MIT licence
Buzz Classic	What buzzcaptions.com calls that same free GitHub app, for Windows, Linux and macOS.	buzzcaptions.com	Free
Buzz Captions, Buzz on macOS	A separate Mac-native version on the Mac App Store: Whisper.cpp models and the OpenAI Whisper API, search, audio playback and inline transcript editing.	Mac App Store link on buzzcaptions.com	Not shown: Apple's US App Store lookup returned no listing for this app id on 26 Oct 2026

Sources:

chidiwilliams/buzz · README (GitHub), fetched 26 Oct 2026
chidiwilliams/buzz · releases (v1.4.5, 23 Aug 2026), fetched 26 Oct 2026
buzzcaptions.com · Buzz Classic and Buzz on macOS, fetched 26 Oct 2026
Apple iTunes lookup for app id 6446018936 (US), fetched 26 Oct 2026

TL;DR

MIT-licensed cross-platform desktop app that wraps Whisper, whisper.cpp, and faster-whisper behind a single GUI. Runs entirely offline; supports file batches, live mic, YouTube URLs, and exports to TXT / SRT / VTT / CSV.

Best for people on Windows, Linux or a Mac who want Whisper without a terminal. The free app is what buzzcaptions.com calls Buzz Classic; a separate Mac-native Buzz Captions was linked to the App Store (no US listing found on 26 Oct 2026).

What it is

Buzz is the open-source cross-platform desktop app for Whisper. File drop, live microphone, multiple model sizes, batch processing — all running locally. Free, MIT-licensed, and the closest OSS equivalent to MacWhisper across all three desktop OSes.

Best for: Non-technical users who want Whisper on their desktop without touching a terminal.
Watch out for: Runs on your own machine, so speed depends on its CPU or GPU and the model size; Mac builds after 1.4.5 need Apple silicon.

Install / use

pip install buzz-captions

Setting Buzz up or fixing an error? Buzz setup guide and common fixes.

Install paths · pick yours

Buzz ships through four channels — pick whichever matches your OS and packaging preference. Every card links to the canonical project / store page; no direct binary URLs.

macOS · Buzz Classic

Free GUI, all backends

The open-source Classic build for Intel + Apple Silicon. Free, MIT-licensed, ships every Whisper backend (Whisper, whisper.cpp, faster-whisper). Distributed through the SourceForge mirror linked from the official docs.

Download via buzzcaptions.com
Latest stable: v1.4.4 · 2026-03-14

macOS · Buzz on App Store

Native paid build

Native macOS rebuild with a Mac-style UI, transcript search, inline editing, and playback. Paid one-time license — Pro tier gets lifetime updates. Skip Classic if you want App Store sandboxing and signed updates.

App Store listing
Linked from the official Buzz Captions homepage

Windows

Installer from SourceForge

Official Windows installer published on SourceForge. The binary is unsigned, so SmartScreen will warn — click "More info → Run anyway" once and you're set. Same Whisper backends as the macOS Classic build.

buzz-captions on SourceForge
12k+ weekly downloads · Open Source Excellence badge

Linux · Flatpak

Flathub package

Sandboxed Flatpak distribution on Flathub. One command and you're running, no Python deps to manage. Same MIT codebase as the other channels.

flatpak install flathub io.github.chidiwilliams.Buzz
Updated alongside upstream releases

Linux · Snap

Canonical store

Snap channel maintained by the author. Pairs with a few apt deps for audio + GTK; install the prereqs once, then connect the password-manager-service plug so the app can persist its settings.

sudo snap install buzz
Stable channel · auto-updates via snapd

Any OS · PyPI

pip-installable, CLI-capable

buzz-captions on PyPI. Useful if you want to script Buzz from a venv, embed it in a pipeline, or run it on a box where you can't install packaged GUIs. Needs Python 3.12 and a system ffmpeg.

pip install buzz-captions
Then run: python -m buzz

Pattern: Classic + SourceForge / Flathub / Snap covers every desktop OS for free. Buy Buzz on macOS only if you specifically want a native-feeling Mac app with App Store updates — the GUI under Classic is functional but not Mac-stylebook. If you want a hosted version with diarization, drop the file in the widget at the bottom of this page.

Setup recipes · pick one and copy

Three working configurations covering the most common Buzz deployments — GUI install on macOS, source build for hacking, and headless batch transcription from a terminal.

1macOS · Buzz Classic from source

The free Buzz (Classic) app from PyPI. The README asks for Python 3.12 and ffmpeg.

# prereqs (Homebrew shown — any package manager works)
brew install python@3.12 ffmpeg

# install Buzz Classic from PyPI
python3.12 -m venv ~/.buzz-venv
source ~/.buzz-venv/bin/activate
pip install --upgrade pip
pip install buzz-captions

# launch the GUI
python -m buzz

Source: Buzz README · Installation ↗, checked 26 Oct 2026 · prefer the prebuilt .dmg? It is on SourceForge ↗

2Run from the GitHub source tree

For hacking on Buzz itself, or running an un-tagged build. Uses poetry for deps and the bundled Makefile.

# clone the repo
git clone https://github.com/chidiwilliams/buzz.git
cd buzz

# install Poetry + deps (Python 3.12 required)
pipx install poetry
poetry env use python3.12
poetry install

# pull bundled translations + run
make translation_mo
poetry run python -m buzz

Source: chidiwilliams/buzz · CONTRIBUTING ↗

3Headless batch · transcribe a folder from the CLI

Drop the GUI entirely. Useful for cron jobs, build pipelines, or running on a server. Outputs SRT/VTT/TXT next to each input.

# install once
pip install buzz-captions

# transcribe every audio file in ./inputs to SRT
for f in inputs/*.{mp3,m4a,wav,mp4}; do
  [ -e "$f" ] || continue
  python -m buzz \
    --task transcribe \
    --model-type whisper \
    --model-size small \
    --output-formats srt txt \
    --output-directory ./transcripts \
    "$f"
done

# swap --model-type to faster_whisper or whisper_cpp
# for ~4× speedup; small/medium/large-v3 sizes available

CLI flags: see Buzz docs ↗. The CLI accepts the same model-type/size matrix as the GUI.

What people actually do with Buzz-style transcription

The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.

Transcribe a whole back catalogue in one runThe archive is the asset, but one-at-a-time upload means it never gets done.…1,000 hours ≈ $480, onceTranscribe every new file in a Drive folderFiles accumulate in a folder nobody opens, and the knowledge in them is invisible to search.…≈ $0.29 per audio hour on the $24 packCut short-form clips out of a webinar automaticallyThe clips worth posting are buried somewhere in a 60-minute recording and finding them by scrubbing costs more than the…60-min webinar ≈ $0.48

Wire it into Amazon S3 n8n Make.com Google Drive Zapier Slack

Features

Speaker diarization	No
Word-level timestamps	Yes
Streaming / real-time	Yes
Languages supported	99
HIPAA eligible	No

Buzz vs Whipscribe

Feature	Buzz	Whipscribe
Category	Open source	Transcription APIs
Pricing	free	$4–$24 one-time packs (credits never expire) · free preview of the opening minutes
Speaker identification	No	Named in the summary, key quotes and chapters
Word timestamps	Yes	Yes
Streaming	Yes	No
Languages	99	99
Platforms	macOS, Linux, Windows	Web, API, MCP

Alternatives to Buzz

OpenAI Whisper

OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 111.4k

whisper.cpp

Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 54.7k

faster-whisper

SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 26.2k

Frequently asked about Buzz

Is Buzz free?

Yes. Buzz is free and MIT-licensed (README, checked 26 Oct 2026). buzzcaptions.com also links a separate Mac App Store version, Buzz Captions; Apple's US lookup returned no listing for it on 26 Oct 2026.

Does Buzz work on Windows and Linux?

Yes. Windows: the installer from SourceForge (unsigned, so choose More info, then Run anyway). Linux: Flatpak, Snap or AppImage. Mac: the .dmg from SourceForge, Apple silicon for versions after 1.4.5. Any OS: pip install buzz-captions on Python 3.12.

Does Buzz support speaker diarization?

The README lists speaker identification in transcribed media as a feature (checked 26 Oct 2026). It runs on your machine, so it adds time to each file.

How does Buzz compare to MacWhisper?

Buzz is free, open source and runs on Mac, Windows and Linux. MacWhisper is a Mac app with a free tier and a paid Pro licence. Both transcribe on your own computer.

Can Buzz transcribe in real time from my microphone?

Yes. Buzz supports live microphone input in addition to file transcription.

What is Buzz?

MIT-licensed cross-platform desktop app that wraps Whisper, whisper.cpp, and faster-whisper behind a single GUI. Runs entirely offline; supports file batches, live mic, YouTube URLs, and exports to TXT / SRT / VTT / CSV.

How do I install Buzz?

With pip: `pip install buzz-captions`. You need Python and, for most audio tools, ffmpeg on your PATH first.

How many languages does Buzz support?

Buzz lists 99 languages. That is the Whisper-family multilingual set, so quality varies by language — English and the large European languages are strongest.

Does Buzz give word-level timestamps?

Yes — Buzz produces timing per word, which is what subtitle cues and clip boundaries need.

Is Buzz HIPAA compliant?

Buzz does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.

What are the limitations of Buzz?

Runs on your own machine, so speed depends on its CPU or GPU and the model size; Mac builds after 1.4.5 need Apple silicon.

Who is Buzz best for?

Non-technical users who want Whisper on their desktop without touching a terminal.

What should I know before choosing Buzz?

Best for people on Windows, Linux or a Mac who want Whisper without a terminal. The free app is what buzzcaptions.com calls Buzz Classic; a separate Mac-native Buzz Captions was linked to the App Store (no US listing found on 26 Oct 2026).

Does Buzz run offline?

Buzz runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Can I use Buzz in the browser?

No — Buzz is a macOS, Linux and Windows application, not a web app. You install it rather than sign in to it.

Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.

What we measured, last 30 days

2,547 recordings, 1,244 audio hours, 66 languages detected. An hour of audio came back in 3.5 minutes for half of the recordings and within 18.0 minutes for nine in ten, measured from the moment the file landed to the finished transcript. Refreshed 2026-10-07; method on how we test.

Transcribe your recordings

Running Buzz yourself? Send the same file here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step

Explore

All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing

Before you load an SRT export into an editor, run it through the SRT checker for overlaps and bad timestamps.
Not sure whether to export SRT or VTT? Subtitle file formats compared shows a real example of each.
Whisper's own translate task writes English text only; to keep the original transcript and get English subtitles on the same timestamps, see translate Spanish audio to English.
Need the gist rather than every word? Summarize audio writes a summary with chapters from the whole transcript.
For recorded classes, lecture notes from a recording adds timestamped chapters and study questions.

Have the recording already?

Skip the setup and send the file or the link: see MP3 to text for long recordings, how to transcribe a podcast and the SRT generator.

Comparing tools before you pay?

If you would rather pay a service than run software yourself: see transcription services from $4.