ScribeWizard
ScribeWizard copied to clipboard
Bklieger
ScribeWizard: Generate organized notes from audio using Groq, Whisper, and Llama3
ScribeWizard: Generate organized notes from audio
using Groq, Whisper, and Llama
Overview • Features • Quickstart • Contributing
Demo of ScribeWizard fast transcription of audio and generation of structured notes
Overview
ScribeWizard is a streamlit app that scaffolds the creation of structured lecture notes by iteratively structuring and generating notes from transcribed audio lectures using Groq's Whisper API. The app mixes Llama 4 Scout and Llama 4 Maverick, utilizing the larger model for generating the notes structure and the faster of the two for creating the content.
Features
- 🎧 Generate structured notes using transcribed audio by Whisper-large and text by Llama
- ⚡ Lightning fast speed transcribing audio and generating text using Groq
- 📖 Scaffolded prompting strategically switches between Llama 4 Maverick and Llama 4 Scout to balance speed and quality
- 🖊️ Markdown styling creates aesthetic notes on the streamlit app that can include tables and code
- 📂 Allows user to download a text or PDF file with the entire notes contents
Example Generated Notes:
| Example | Youtube Link |
|---|---|
| Transformers Explained by Google Cloud Tech | https://www.youtube.com/watch?v=SZorAJ4I-sA |
| The Essence of Calculus by 3Blue1Brown | https://www.youtube.com/watch?v=WUvTyaaNkzM |
As with all generative AI, content may include inaccurate or placeholder information. ScribeWizard is in beta and all feedback is welcome!
Quickstart
[!IMPORTANT] To use ScribeWizard, you can use a hosted version at scribewizard.streamlit.app. Alternatively, you can run ScribeWizard locally with Streamlit using the quickstart instructions.
Hosted on Streamlit:
To use ScribeWizard, you can use the hosted version at scribewizard.streamlit.app
Run locally:
Alternative, you can run ScribeWizard locally with streamlit.
Step 1
First, you can set your Groq API key in the environment variables:
export GROQ_API_KEY="gsk_yA..."
This is an optional step that allows you to skip setting the Groq API key later in the streamlit app.
Step 2
Next, you can set up a virtual environment and install the dependencies.
python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt
Step 3
Finally, you can run the streamlit app.
python3 -m streamlit run main.py
Details
Technologies
- Streamlit
- Llama on Groq Cloud
- Whisper-large on Groq Cloud
Limitations
ScribeWizard may generate inaccurate information or placeholder content. It should be used to generate notes for entertainment purposes only.
Contributing
Improvements through PRs are welcome!
Changelog
v0.1.0
This release is an initial release of the application codebase. It includes the following features:
🎧 Generate structured notes using transcribed audio by Whisper-large and text by Llama
⚡ Lightning fast speed transcribing audio and generating text using Groq
📖 Scaffolded prompting strategically switches between Llama 4 Maverick and Llama 4 Scout to balance speed and quality
🖊️ Markdown styling creates aesthetic notes on the streamlit app that can include tables and code
📂 Allows user to download a text or PDF file with the entire notes contents
Future Features:
- Create summary version of transcript, batching into sections of n characters.
- Allow upload of multiple audio files
Bklieger