Welcome to the "Talk to Me" repository, a project designed to seamlessly integrate audio recording, speech recognition, text generation, and text-to-speech conversion. This software provides a dynamic and interactive audio experience.
- Audio Recording: Capture high-quality audio using PyAudio.
- Speech Recognition: Convert recorded audio to text with Google's Speech Recognition API.
- Text Generation: Utilize Google Generative AI to process and generate text content.
- Text-to-Speech Conversion: Convert generated text to speech and save it as an MP3 file using gTTS.
- Audio Playback: Play the generated audio using Pygame.
- PyAudio: For capturing and handling audio data.
- Wave: To save recorded audio in WAV format.
- SpeechRecognition: For converting audio to text using Google's Speech Recognition API.
- gTTS: For converting text to speech and saving as an MP3 file.
- Pygame: To play audio files.
- Google Generative AI: Leverage advanced generative AI models for content generation.
- Clone the repository:
git clone https://github.com/Ankit1017/TalkToMe.git
The main script captures audio, converts it to text, processes the text with generative AI, and converts it back to audio. If the phrase "OK Google" is detected in the audio, the process halts; otherwise, it continues with further processing and playback.
Contributing We welcome contributions! Please feel free to submit issues and pull requests to improve this project.
License This project is licensed under the MIT License.