✨ What I Do

• 🗣️ Voice & TTS: Streaming ASR → LLM → TTS pipelines, prosody fine-tuning, and interruptible playback.
• 📡 Real-time: WebRTC integration with VAD, barge-in support, and chunked synthesis.
• Product & Agents: Conversation-first design with memory, tool calling, and action visualization in multi-modal interactions.
• Engineering: Distributed task scheduling, voice dubbing platforms, and TTS ecosystem products.

🔍 Interests

• 🤖 Conversational AI & NLP
• 🎙️ Voice Interaction & Speech Technologies
• 📡 Real-time Communication (RTC)
• 🧠 LLMs & Autonomous Agents

🌱 Currently Learning

• Low-latency voice processing optimization
• Multi-modal AI interactions (Speech + UI)
• Dialogue quality evaluation frameworks