This project is a speech processing application that utilizes OpenAI's APIs for transcription and text-to-speech (TTS) conversion. It includes functionality for transcribing audio, generating responses based on transcriptions, and converting text to speech using OpenAI's TTS API.
To transcribe audio and generate responses, the project uses OpenAI's transcription and completion models. The generate_response function is used to generate responses based on transcriptions, and the generate_tts_response_openai function is used to convert text to speech using OpenAI's TTS API.
To install the required packages, run the following command:
pip install -r requirements.txtTo get started with the project, follow these steps:
- Rename template.json to config.json
- Set up the OpenAI API key in the configuration file.
- Use the provided functions to transcribe audio, generate responses, and convert text to speech.
If you would like to contribute to the project, please fork the repository and submit a pull request with your changes.