Whispering
Whispering is a speech-to-text app inside the Epicenter monorepo, under AGPL-3.0-or-later. Press a shortcut, speak, and it transcribes with a provider you choose, cloud or a self-hosted endpoint, optionally polishes the text, and pastes it at the cursor on desktop. It is built from source with Bun rather than downloaded, and it stores your data in a local-first store the monorepo describes as yours to keep.
What does Whispering do?
Whispering's own summary is "Press shortcut → speak → get text." It "records speech, transcribes it with a provider you choose, optionally polishes the transcript, and delivers the text". The provider can be a cloud service or a self-hosted endpoint in both the browser and desktop builds; on-device transcription with GGUF models is available only in the Epicenter desktop build, because that is where the native model runtime lives.
System-wide shortcuts and pasting at the active cursor work on desktop; the browser build falls back to the clipboard. The README says audio "leaves the device only when the selected transcription provider requires an upload".
Key facts
- Licence: AGPL-3.0-or-later on every package and app; the root LICENSE is an index rather than a licence text, which is why GitHub's API reports none. Versions published under the former MIT tier stay MIT.
- Its own summary: "Press shortcut → speak → get text."
- Transcription providers: cloud or a self-hosted endpoint in both browser and desktop builds; on-device GGUF transcription only in the Epicenter desktop build, where the native model runtime lives.
- Delivery: system-wide shortcuts and paste at the active cursor on desktop; clipboard fallback in the browser.
- Audio leaves the device only when the selected transcription provider requires an upload, per the README.
- Built with bun install then bun dev:whispering or bun dev:epicenter; desktop builds need Rust for Tauri. No installer download is listed.
- The former standalone repository at braden-w/whispering is archived and redirects here; the monorepo says the previous data stack was deleted rather than migrated.
- The monorepo describes a hosted Epicenter sync service with billing and a self-host reference deployment; no prices are stated.
What does it replace, and where does it fall short?
Whispering replaces Wispr Flow and Superwhisper for someone who wants to pick the transcription provider themselves and keep their data in a store they own. The monorepo's stated principle is "Your data outlives the app that wrote it."
Where it falls short: neither README lists an installer to download; you build from source. Which speech models, speaker labelling and meeting capture are not described. The former standalone repository at braden-w/whispering is archived and redirects here, and the monorepo's README says the previous data stack was deleted rather than migrated.
How does Whispering run?
Clone the monorepo, bun install, then bun dev:whispering or bun dev:epicenter. Desktop builds need Rust for Tauri. Whispering does not own a native shell of its own: the README says "Epicenter owns the only Tauri runtime". There is no hosted browser deployment any more. The maintainers describe a hosted Epicenter sync service with billing and a self-host reference deployment; no prices are stated.
The licence is AGPL-3.0-or-later on every package and app. The root LICENSE is an index rather than a licence text, which is why GitHub's API reports no licence. An MIT tier existed until August 2026 and was dissolved; versions already published under MIT stay MIT.
Who is Whispering for?
A developer who wants to run dictation from source, choose the provider, and keep the transcripts in a local-first store. Someone who wants a downloadable installer should pick Handy, VoiceInk or OpenWhispr.
What limits does the README state?
"A hosted web runtime with a host-owned replica is refused, and so are third-party installed apps, for now." "Signed-in sync sends your data to a trusted server that reads it in plaintext." On-device transcription "is available only through Epicenter".
Questions people ask
Is Whispering open source?
Yes. Every package and app in the Epicenter monorepo is AGPL-3.0-or-later, an OSI approved copyleft licence. GitHub shows no licence only because the root LICENSE file is an index pointing at the per-package licences rather than a licence text itself.
Can I use Whispering commercially?
Yes, under the AGPL-3.0, which permits commercial use and requires that anyone who runs a modified version as a network service offers its source. For a dictation app you run yourself that obligation rarely bites; for a hosted product built on it, read the licence first.
Does Whispering run offline?
Only in the Epicenter desktop build, which has the native model runtime for on-device GGUF transcription. The standalone browser or desktop Whispering build sends audio to whichever cloud or self-hosted provider you configure, and the README says audio leaves the device only when that provider requires an upload.
How does Whispering compare with Wispr Flow?
Whispering gives you the same shortcut-speak-paste loop with your own choice of transcription provider and a data store you own, at the cost of building it from source. Wispr Flow ships as an installed product with its polish built in. The open-source alternatives to Wispr Flow page compares it with Handy, VoiceInk and OpenWhispr.
Where do I download Whispering?
There is no installer listed in either README. Clone the Epicenter monorepo, run bun install, then bun dev:whispering for the app or bun dev:epicenter for the desktop shell, with Rust installed for Tauri. The README also says there is no hosted browser deployment any more.
Sources
- Epicenter root README and LICENSE index: github.com/EpicenterHQ/epicenter, read 2026-09-16.
- Whispering README: apps/whispering, read 2026-09-16.
Compared with the others
On the open-source alternatives to Wispr Flow page, Whispering is the pick for choosing your own transcription provider. AGPL-3.0, inside the Epicenter monorepo. Any cloud or self-hosted transcription endpoint, an optional polish step, and a local-first store you own.
Also on that page: Handy for all three desktops, nothing else running, VoiceInk for a mac, with modes per application, FluidVoice for a mac with the newest local models.
On the open-source alternatives to Superwhisper page, Whispering is the pick for choosing your own transcription provider. AGPL-3.0, inside the Epicenter monorepo. Any cloud or self-hosted transcription endpoint, an optional polish step, and a local-first store you own.
Also on that page: VoiceInk for a mac, with modes per application, Handy for all three desktops, nothing else running, FluidVoice for a mac with the newest local models.
More voice dictation apps
A free, offline push-to-talk dictation app for macOS, Windows and Linux that runs Whisper or NVIDIA Parakeet on your own machine and pastes the text at your cursor, under MIT.
A GPL-3.0 macOS dictation app that runs Nemotron, Parakeet, Cohere Transcribe, Apple Speech or Whisper on the device, with command and write modes, per-app prompts, and an optional closed local enhancement model.
A dictation and meeting-notes app under MIT that runs Whisper or Parakeet locally or cloud models with your own key, detects Zoom, Teams and FaceTime calls, and labels speakers on device.
A macOS dictation app under GPL-3.0 whose README names Superwhisper and Wispr Flow as the tools it replaces, with local models, per-app modes, a personal dictionary and an AI assistant mode.
An Apache-2.0 macOS dictation app that calls Gemini 3.5 Transcribe with your own key, writes audio to disk from the first millisecond for crash safety, and inserts polished text at your cursor without an account.
A free, open-source dictation app for macOS under Apache-2.0 that holds a shortcut, listens, and pastes the text where your cursor is, with Whisper, NVIDIA Parakeet or Apple on-device speech recognition.
Added September 16, 2026. Every claim above comes from the project's README, LICENSE or model card, read on September 16, 2026, or from the GitHub API on the date shown in the panel. Found an error? Write to reveneau@licheo.com and it is fixed in the next weekly pass. Repository: github.com/EpicenterHQ/epicenter.
Want Whispering running on your own servers?
Reveneau sets it up on your hardware, connects it to your product, and builds the software around it.