Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/aviaryan/voice-writing-electron
A real-time, instant dictation desktop application built on Electron that uses Whisper and GROQ under the hood
https://github.com/aviaryan/voice-writing-electron
electron groq groq-api svelte whisper whisper-cpp
Last synced: 2 months ago
JSON representation
A real-time, instant dictation desktop application built on Electron that uses Whisper and GROQ under the hood
- Host: GitHub
- URL: https://github.com/aviaryan/voice-writing-electron
- Owner: aviaryan
- License: apache-2.0
- Created: 2024-08-05T20:03:30.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-08-15T13:19:41.000Z (4 months ago)
- Last Synced: 2024-09-29T10:50:38.779Z (3 months ago)
- Topics: electron, groq, groq-api, svelte, whisper, whisper-cpp
- Language: JavaScript
- Homepage:
- Size: 330 KB
- Stars: 20
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🗣️📝 VoiceWriting
VoiceWriting is a Whisper based Desktop application to write using your voice.
It works in real-time and even fixes common grammatical, punctuation and other issues in your speech.
Give it a try by following the instructions below, or check out the demo 📹 below 👇🏻.
https://github.com/user-attachments/assets/8eaa697b-ffeb-4aea-8566-10a711a59b74
## 🛠️ Easy Setup
#### 1. Clone and install dependencies
```sh
git clone https://github.com/aviaryan/voice-writing-electron.git
yarn install
cp .env.copy .env
```
#### 2. Populate `.env` file
1. Add the absolute path for whisper.cpp's `stream` executable in `STREAM_EXECUTABLE_PATH`. Learn more about [stream](docs/DEPENDENCIES.md#stream).
2. Add the absolute path for GGML Whisper `model` in `MODEL_PATH`. Learn more about [model](docs/DEPENDENCIES.md#model).
3. Fill in the GROQ API Key. Learn more about [Groq API key](docs/DEPENDENCIES.md#groq).
Example -
```ini
GROQ_API_KEY=gsk_abcdksk2kkskssd
STREAM_EXECUTABLE_PATH=/Users/john/dev/stream
MODEL_PATH=/Users/john/dev/ggml-small.en.bin
```
#### 3. Start the application
```sh
yarn start
```
#### 4. Start speaking!
You should have the application ready now and you can start using it as shown in the video below. Make sure to unmute 🔉 the video before playing.
https://github.com/user-attachments/assets/8eaa697b-ffeb-4aea-8566-10a711a59b74
## 📦 Distributing as an app
1. Ensure `.env` has all the values as `.env` file gets packaged with the application.
2. Run `yarn build`. It builds the app only using `target: dir` on Mac. Use `target: dmg` to build dmg.
3. Check `dist` folder for the app.