Whispering

Whispering is a speech-to-text app for people who want to dictate text into other applications and choose where transcription happens. Its desktop app runs within Epicenter, but the project currently lists it at compile status after a storage migration.

• Transcription providers: Choose a cloud provider or self-hosted endpoint, or use on-device GGUF transcription through Epicenter's native runtime.
• Transcript polishing: Optionally have the app polish a transcript before delivering the text.
• Desktop dictation: System-wide shortcuts control recording, a floating window shows recording activity, and native text delivery can paste at the active cursor when permissions allow.

Whispering is free and open source under AGPL-3.0-or-later. Settings and recording metadata stay local first. Audio leaves your device when the chosen transcription provider requires an upload; provider connections can be direct, through the hosted Epicenter gateway, or through a self-hosted endpoint.

Signed-in synchronization sends application data to a server that can read it in plaintext. Epicenter offers hosted infrastructure and a community-supported self-hosted instance. The browser build is no longer a supported deployment target, though an older hosted copy may still be accessible. The storage migration doesn't import data from the previous system.