A simple interface to the OpenAI GPT-3 models with speech to text for input and text to speech for the output from OpenAI.

Optionally create a new Python environment and active it:

# create a new environment in the current directory called env
python3 -m venv env

# activate the environment
source env/bin/activate

Install dependencies:

# Mac OSX
brew install portaudio
brew link portaudio

# save the output of this command
brew --prefix portaudio

Run

sudo vi $HOME/.pydistutils.cfg

and paste the following text replacing the values with the output saved from above:

[build_ext]
include_dirs=<PATH FROM STEP 3>/include/
library_dirs=<PATH FROM STEP 3>/lib/

Finally, run the following to install all required Python packages:

pip install -e .

python gpt3_assistant/main.py --log-level=INFO --open-ai-key=<OPEN API SECRET KEY HERE>

Start speaking and turn up your volume to hear the AI assistant respond.

Say the word "exit" to stop the application.

Specify both the LANGUAGE and TOP_LEVEL_DOMAIN vars to override the default English (United States)

python gpt3_assistant/main.py --open-ai-key=<OPENAI_KEY> --lang=en --tld=com

• English (United States) DEFAULT
  • LANGUAGE=en TOP_LEVEL_DOMAIN=com
• English (Australia)
  • LANGUAGE=en TOP_LEVEL_DOMAIN=com.au
• English (India)
  • LANGUAGE=en TOP_LEVEL_DOMAIN=co.in
• French (France)
  • LANGUAGE=fr TOP_LEVEL_DOMAIN=fr

See Localized 'accents' section on gTTS docs for more information

Sort all imports with:

isort --multi-line 3 --profile black --python-version 38 gpt3_assistant

Run black gpt3_assistant to automatically reformat all source files based on the default configuration.

Run pytest to run all unit tests.

Get the coverage with:

coverage run -m pytest tests

View the coverage report:

coverage report --fail-under=90 --include="gpt3_assistant/*"

SpeechRecognition library docs

Google Translate Text-to-Speech API (gTTS)