Topic API
AI API Token Optimization: Cut Costs
A practical guide to AI API token optimization. See how conversation history, RAG documents, tool outputs and response length were reviewed to reduce input tokens from about 8,000 to 1,600 while preserving the information needed to answer users.
Turning Google Colab into an API Server to Run Speech-to-Speech Voice AI
This PoC turns Google Colab into a temporary WebSocket server for speech-to-speech AI. It combines faster-whisper large-v3, Gemini 2.5 Flash-Lite, VOICEVOX and Silero VAD, then improves latency through sentence buffering, streaming responses and parallel TTS generation.
What We Learned Building Voice AI with Gemini: The Major Difference Between a PoC and a Commercial Service
A Gemini Live API PoC can deliver real-time voice conversations quickly, but production introduces concurrency, quotas, observability, model lifecycle and device-specific audio issues. This article explains why the architecture moved from direct browser access to LiveKit and Vertex AI.
Part 1: Introduction to gRPC Framework
gRPC is a robust open-source RPC framework used to build scalable and fast APIs for modern applications.
Introducing Gen Code Tool for API Development
Are you tired of repetitive coding? Introducing "Gen Code Tool," our solution for automating API development.
JWT in Production: Best Practices for Authentication
JSON Web Tokens (JWT) are the go-to solution for handling user authentication and authorization in web applications.
