Skip to content

v0.0.2 Windows support; history optional and encrypted; textual tweaks #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tobitege wants to merge 2 commits into
base: main
Choose a base branch
from
+1,387 −762
Open

v0.0.2 Windows support; history optional and encrypted; textual tweaks #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a479dc
v0.0.2 Windows support; history optional and encrypted; textual tweaks
tobitege Mar 21, 2025
31046dd
OpenAI API support
tobitege Mar 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 36 additions & 0 deletions CHANGES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,36 @@
# Change Summary

## Version 0.0.2

### Cross-Platform Support

- Added proper Windows platform support
- Made UI and controls adapt to the specific platform
- Implemented platform-specific shortcuts (Command+Shift+Space on macOS, Ctrl+Shift+Space on Windows)
- Updated requirements to reduce deprecated packages warnings

### User Experience Improvements

- Made the API key management more clear and fixed empty key handling
- Disabled post-processing by default for new installations
- Improved explanatory text throughout the application

### History Features

- Added toggle to enable/disable history recording
- Added "Clear History" button with confirmation dialog
- Implemented secure encryption of history data using system keychain/credential store
- Added status indicator to show encryption availability

### Security Improvements

- Utilized Electron's safeStorage API for encrypting sensitive transcript data
- Implemented proper error handling for encryption/decryption operations

### Other Improvements

- Various code organization improvements and refactoring

## Version 0.0.1

- Initial release
30 changes: 21 additions & 9 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,14 @@
# HotMic

A lightweight desktop application that transcribes audio using the Groq API and Whisper-large-v3 model.
A lightweight desktop application that transcribes audio using either Groq or OpenAI APIs with the Whisper-large-v3 model. While an API key is required for transcription, the post-processing feature (which formats the transcription output) is optional.

## Features

- Press a global shortcut to start/stop recording
- Audio is sent to Groq API for transcription
- Cross-platform support for both Windows and macOS
- Press a global shortcut to start/stop recording (platform-specific defaults)
- Audio transcription using Groq or OpenAI Whisper API
- Multiple transcription model options (whisper-large-v3, gpt-4o-transcribe, etc.)
- Optional post-processing with Groq or OpenAI LLM to format transcripts
- Results are automatically copied to clipboard
- Visual feedback during recording and processing
- Configurable keyboard shortcut
Expand All @@ -14,26 +17,35 @@ A lightweight desktop application that transcribes audio using the Groq API and

1. Clone this repository
2. Install dependencies:
```

```bash
npm install
```

3. Run the application:
```

```bash
npm start
```

## Configuration

1. Sign up for a Groq API account at [https://console.groq.com](https://console.groq.com)
2. Get an API key
1. Choose a provider for speech-to-text (Groq or OpenAI)
2. Get an API key from your chosen provider:
- For Groq, sign up at [https://console.groq.com](https://console.groq.com)
- For OpenAI, sign up at [https://platform.openai.com](https://platform.openai.com)
3. Enter your API key in the app settings
4. Select your preferred transcription model
5. (Optional) Enable post-processing to format transcripts

## Usage

1. Press the configured global shortcut (default: Ctrl+Shift+Space) to start recording
1. Press the configured global shortcut (default: Ctrl+Shift+Space on Windows, Command+Shift+Space on macOS) to start recording
2. Speak into your microphone
3. Press the shortcut again to stop recording and begin transcription
4. Once transcription is complete, the text will be copied to your clipboard
- By default, you'll get the raw transcription text from the Whisper model
- If post-processing is enabled, you'll get formatted text based on a customizable prompt (default: formats text as a professional email)

## Development

Expand All @@ -48,4 +60,4 @@ A lightweight desktop application that transcribes audio using the Groq API and

## License

MIT
MIT
Loading