Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.
Go to file
2023-05-13 15:50:42 -04:00
custom_speech_recognition refactor audio recording 2023-05-13 10:36:00 -04:00
.gitignore update requirements 2023-05-12 12:00:03 -04:00
AudioRecorder.py refactor audio recording 2023-05-13 10:36:00 -04:00
AudioTranscriber.py Better phrase timout 2023-05-13 11:42:02 -04:00
GPTResponder.py bug fixes 2023-05-13 11:41:10 -04:00
main.py minor refactoring 2023-05-13 10:46:05 -04:00
prompts.py first commit 2023-05-07 22:10:48 -04:00
README.md Update README.md 2023-05-13 15:50:42 -04:00
requirements.txt added transcript limit 2023-05-12 21:08:31 -04:00
tiny.en.pt first commit 2023-05-07 22:10:48 -04:00

ecoute

install instructions:

git clone https://github.com/SevaSk/ecoute

in ecoute folder:

pip install -r requirments.txt

create keys.py file and fill it with the line OPENAI_API_KEY = "API KEY" where "API KEY" will be a string containing your open API api key

python main.py