feat: Enhance audio processing and transcription features

refactor: load_dotenv only when local

feat: Implement tools calling

Update backend/tts.py

Update backend/tts.py

Update backend/systemprompt.py

Update backend/models.py

Update backend/asr.py

Update backend/systemprompt.py

Update backend/models.py

Update backend/asr.py

Update backend/main.py

Update backend/models.py

Update backend/utils.py

Update backend/utils.py

Update backend/models.py

Update backend/utils.py

Update backend/models.py

Update backend/models.py

Update backend/models.py

Upload 23 files

Delete backend

Upload 32 files