videosdk.live

ai agents

Introducing the Nvidia Speech to Text Plugin in VideoSDK

Learn how to integrate NVIDIA STT with the VideoSDK Agents SDK to generate fast, accurate, and production-ready transcriptions.

ai agents

Introducing the MurfAI Text To Speech Plugin in VideoSDK

Learn how to integrate Murf AI Text-to-Speech with VideoSDK Agents to generate natural, expressive, and low-latency voice output for AI agents.

ai agents

Introducing the Nvidia Text to Speech Plugin in VideoSDK

Learn how to integrate NVIDIA Riva TTS with the VideoSDK Agents SDK to deliver real-time, low-latency speech that makes AI voice agents sound natural, responsive, and production-ready.

plugins

Introducing the Gladia Speech to Text Plugin in VideoSDK

We’re introducing the Gladia Speech-to-Text plugin for VideoSDK. With multilingual support, instant partial results, and handling of mixed languages, it provides a reliable speech input layer for voice-driven applications.

ai agents

Introducing Testing and Evaluation in AI Voice Agents

Learn how to run testing and evaluation for AI voice agents using the VideoSDK Agent SDK, including STT, LLM, and TTS benchmarking, latency metrics, and LLM-based response judging.

ai agents

How to Build an AI Voice System Using Real-Time Multi-Agent Switching

In this blog you'll learn about how to build an AI systems with multi-agent switching that intelligently transfer control between specialized agents. Keep conversations natural, tasks organized, and users engaged by letting each agent focus on what it does best.

ai telephony

How to enable Voice Mail Detection in AI Voice Agents

Learn how Voice Mail Detection improves outbound calling by identifying voicemail systems automatically. Instead of wasting time speaking into silence, your agent can leave a message or end the call smoothly, helping save call time, reduce costs, and improve overall calling efficiency.

Product Updates Featured

Product Updates - December 2025 : New Billing & Pricing, AI Agents with Graphs & Fallback, and More!

Announcing our new transparent billing system and pricing for 2026! This month's update also gives your AI agents a "brain" with Conversational Graphs, makes them unstoppable with Provider Fallback, and adds powerful new video optimization features across all core SDKs.

ANNOUNCEMENT Featured

Announcing New Pricing: Free Credits, Simpler Pricing, and a Smarter Billing Dashboard

VideoSDK introduces a new Pay-As-You-Go On-Demand model and a redesigned Billing Dashboard featuring a $20 free balance, prepaid wallet, and real-time usage controls.

ai telephony

How to Transfer Calls in AI Voice Agents Using SIP Telephony

Learn how to automatically transfer ongoing SIP call to another phone number without disconnecting the call or redialing using Call Transfer in SIP Telephony

ai telephony

How to enable DTMF Events in Telephony AI Agent

Learn how DTMF input powers reliable, menu-driven voice interactions. This blog explores common use cases and shows how VideoSDK voice agents process real-time keypad events to drive precise call flows.

preemtive-response

How to enable preemptive response in AI Voice Agents

Learn how Preemptive Response reduces voice AI latency by streaming partial transcripts to the LLM, enabling faster and more natural conversational agents.

Product Updates Featured

Product Updates - November 2025 : Agent Runtime, WHIP/WHEP and Realtime Data Store

This month, we're changing the game for AI development. Introducing the Agent Runtime, our new no-code/low-code agent builder! Plus, WHIP/WHEP docs, sync data with the new Realtime Store, and check out our full suite of new quickstart guides.

Product Updates Featured

Product Updates - October 2025 : Supercharged AI Agents, New SDK Features & More

This month's update is all about AI! We're unveiling Namo, our powerful in-house turn detection model for truly natural conversations, and a new WhatsApp AI Voice Agent Quickstart. Plus, get the details on major Android video control features and new React monitoring hooks.

ai agents

How to handle speech in AI Voice Agents with Namo Turn Detection Model

Learn how to make your AI Voice Agents sound natural and interruption-aware using the NAMO Turn Detection model - a semantic, transformer-based system that replaces silence timers with true speech understanding.

ai agents

How to Build an AI Voice Agent Using the RAG Pipeline and VideoSDK

Learn how to build an AI Voice Agent with Retrieval-Augmented Generation (RAG). This guide walks through ingestion, embeddings, retrieval, and real-time voice response with complete code examples.

Namo-Turn-Detection-v1: Semantic Turn Detection for AI Voice Agents

Turn-taking, the ability to know exactly when a user has finished speaking, is the invisible force behind natural human conversation. Yet most voice agents today rely on Voice Activity Detection (VAD) or fixed silence timers, leading to premature cut-offs or long, robotic pauses. We introduce state of the art NAMO

Developer Blog

Build a AI Phone Agent for Inbound & Outbound SIP Calls

Build and deploy a AI phone agent with VideoSDK—complete step-by-step guide from coding to live phone integration.

Developer Blog

Top AI Voice Agent Use Cases Across Industries in 2025

AI voice agent use cases in 2025 across industries, showcasing how conversational AI boosts efficiency, customer satisfaction, and business growth.

Developer Blog

How to Build an AI Voice Agent in Minutes in 2025

Learn how to build an AI voice agent in minutes in 2025 using top conversational AI tools, voice automation, and real-time speech technologies.

Developer Blog

10 Best AI Voice Agents and Platforms in 2025

Explore 10 top AI voice agents & platforms (2025) with conversational AI comparisons, virtual assistant features, voice automation tips, and real use cases.

Developer Blog Featured

Deploy VideoSDK Telephony Voice Agents on Cerebrium

AI telephony agent with VideoSDK & Cerebrium. A step-by-step guide with full code to deploy your own voice solution.

Developer Blog

Build a Video Calling App with Call Trigger in Flutter - iOS using Firebase and VideoSDK

Build an iOS video calling feature that triggers native call screens, manages VoIP notifications, and handles answering or rejecting calls seamlessly.

Developer Blog

Build a Video Calling App with Call Trigger in Flutter - Android using Firebase and VideoSDK

Create a cross-platform video calling app for Android with native call triggers using Flutter, Node.js, Firebase, VideoSDK, and Telecom Framework.

Developer Blog Featured

Build a Conversational Flow AI Agent with Voice Activity & Turn Detection

Build a production-quality, self-contained Voice Agent featuring advanced conversational flow, voice activity detection (VAD), and turn detection.