Text-to-Speech / Speech Transcription Apps

Sample Python projects that use the OpenAI Speech-to-Text API (gpt-4o-transcribe) to transcribe microphone audio in real time.

Apps

File	Description
speechgpt.py	Console-based transcription — writes output to a text file
speechgptTkinter.py	Desktop GUI (Tkinter) with microphone selector, start/stop buttons, and live transcript

Setup

1. Install Python

Make sure Python 3.10+ is installed. You can download it from python.org.

2. Create a virtual environment (recommended)

python -m venv venv

# Windows
venv\Scripts\activate

# macOS / Linux
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Configure your OpenAI API key

Create a .env file in the project root

OPENAI_API_KEY=sk-proj-your-key-here

Get your API key from platform.openai.com/api-keys.

Important: The .env file is git-ignored so your key stays out of version control.

5. Run

# Local version
python speechifyTkinter.py

# ChatGPT Transcribe version
python speechgptTkinter.py