epicenter
epicenter copied to clipboard
Press shortcut → speak → get text. Free and open source. More local-first apps soon ❤️
### Feature Description Whispering currently excels at converting speech to text (STT). A powerful complement would be adding **Text-to-Speech (TTS)** as a separate, standalone feature—not just for reading back transcriptions,...
One thing that's been hindering my workflow is the **ease of use of transformations**. I'm coming from the software called [SpeechPulse](https://speechpulse.com/), where you can transform highlighted text. You could: >...
I only see .txt export format. Would love to export .srt files.
This PR hardens the transcription pipeline so Whisper C++ failures on Linux no longer take down the desktop app. Instead of crashing on poisoned mutexes we now surface ModelLoadError back...
### Bug Description ### Bug: Given that Whispering doesn't add a space at the end of sentences, I've added the following Regex: Find Text: ```(.*)``` Replace Text: ```$1 ``` (one...
### Bug Description With Groq (haven't tried others). ### Steps to reproduce: 1. In Settings, set Temperature to say 0.8. 2. It'll get saved now. If you go back to...
### Bug Description ### Bug: Missing the icons of audio files in the recording list with the 7.7..0 and running the migration from past records. ### Expected behavior: I've restarted,...
### Feature Description It would be great if Whispering could automatically copy or move the saved Markdown file to another folder, optionally converting it into another format such as Org-mode....
## Summary This PR adds support for custom API endpoints (Ollama, LM Studio, llama.cpp, etc.) in transformations, enabling fully offline, privacy-preserving AI transformations using local models. Users can now configure...
## Summary This PR adds automatic media pause/resume functionality for macOS users during recording sessions. When enabled, Whispering will automatically pause Apple Music and Spotify when starting a recording and...