Skip to content

Instantly share code, notes, and snippets.

View rahulmanuwas's full-sized avatar

Rahul rahulmanuwas

View GitHub Profile
#!/usr/bin/env python3
"""
Human quality transcripts from audio files using
AssemblyAI for transcription and Google's Gemini for enhancement.
Requirements:
- AssemblyAI API key (https://www.assemblyai.com/)
- Google API key (https://aistudio.google.com/)
- Python packages: assemblyai, google-generativeai, pydub
Me:
I am looking to build a simple GUI site that allows me to paste in some text, click "rewrite", and get rewritten, cleaned-up text back. This input text is ran through the Claude API to rewrite it. The GUI should be very simple. I just want a text box for input and a text box for output. I also two sliders on the side with labels on the ends:
Tone: casual on the left, formal on the right. The middle instructs the model to keep the tone/voice the same.
Length: shorter on the left, longer on the right.
Above these sliders, I want a model selector dropdown that let's me pick which Claude model to use. I also want a copy text button under the output textbox. The three Claude models are:
claude-3-opus-20240229. Display name "Claude 3 Opus".
claude-3-sonnet-20240229. Display name "Claude 3 Sonnet".
claude-3-haiku-20240307. Display name "Claude 3 Haiku".