Feature Request: Multimodal Support - Speech and Image Processing

[HsiangNianian]

We envision iamai evolving into a truly multimodal toolkit. By adding support for speech and image processing, we can enable robots to handle richer forms of communication, including voice commands and image recognition.

Speech Recognition (ASR): Implement speech-to-text functionality with Vosk or another ASR system to enable voice interaction.
Speech Synthesis (TTS): Implement text-to-speech to allow the robot to respond vocally.
Image Processing: Add support for basic image processing tasks like Optical Character Recognition (OCR) and image classification (using pre-trained models like ResNet or MobileNet).

Expected Outcome

• A more interactive experience where robots can both understand and generate speech and recognize images.
• Facilitate more advanced user interactions beyond just text, such as voice commands and image-based queries.