Latest Blog Posts

A deep dive into the VibeVoice realtime TTS websocket extension in TEN Framework, including architecture, configuration, flow, and expected results.

A deep dive into implementing Google's latest text-to-speech models with the TEN framework

Plug Sarvam's low-latency Bulbul voices into TEN with the bundled HTTP TTS extension.

Learn how to build a real-time voice agent with memory, powered by TEN Framework and memU, that remembers your name, preferences, and past conversations.

Build a TEN agent that streams audio over Agora RTC while sending low-latency text/data over Agora RTM.

A quick start guide to building your first real-time multi-language AI application with TEN Framework. Set up a voice transcription demo using Go, Python, and TypeScript in under 5 minutes.

Learn how to build production-ready voice AI applications using WebSockets instead of WebRTC. Explore TEN Framework's simple yet powerful JSON-based protocol for real-time STT → LLM → TTS pipelines.

Learn how turn detection takes voice conversations beyond simple speech recognition. Discover why understanding conversational context matters more than ever.

Discover how TEN VAD improves voice assistant accuracy and responsiveness. Learn the fundamentals of Voice Activity Detection and why it matters for conversational AI.

A walkthrough of wiring Speechmatics diarization into a TEN agent, streaming transcript chunks to the browser, and labelling every word with the right speaker.

Build AI-powered phone call systems that handle both inbound and outbound calls with real-time voice conversation capabilities.

Walk through the TEN transcription example that streams speech, cleans it with an LLM, and renders polished text in the browser.

Using Node.js to build a real-time voice agent with TEN Framework.

Build your own voice assistant with TEN-Agent.