September 2025 Summaries

The Vonage Documentation MCP Server offers developers a new method to access Vonage documentation directly within their development environments or AI assistants, such as VS Code, Cursor, and Claude, enhancing productivity by enabling in-line, context-aware documentation queries. By integrating this Model Context Protocol server, developers can maintain focus without the distraction of searching for documentation externally, leading to faster iteration and more accurate results. Setup is straightforward, involving simple configuration adjustments in VS Code, Cursor, and Claude Desktop, allowing seamless connectivity to the Vonage documentation. The initiative aims to streamline developers' workflows and ensure immediate access to necessary technical information, ultimately supporting a more efficient development process.

In the guide, Dwane Hemmings explains how to integrate the Vonage Live Captions API into a Node.js application to enhance accessibility and focus in video calls by providing real-time captions. It walks readers through setting up server endpoints to start and stop live captions, using a sample Node.js server application available for deployment. The guide also covers how to configure the frontend to interact with these server endpoints, making it possible to initiate and terminate captioning in a video session. It highlights the process of generating necessary tokens for video call participation, emphasizes the broad support for various languages across regional media zones, and offers sample code to illustrate the implementation. Additionally, it encourages ongoing engagement through a developer community and newsletter subscription for updates on tutorials, releases, and events.

In a tutorial by Amanda Cavallaro, developers are guided through building a Node.js application that provides visual weather forecasts via RCS using the Vonage Messages API and Google AI. The app fetches weather data, generates descriptive images with Google's Imagen model, and compiles text summaries using Gemini, which is then sent as a rich card to users. Key requirements include installing Node.js, registering an RCS Business Messaging agent, and using an API tunneling service like ngrok. Developers will need various API keys and a Vonage API account to authenticate and set up the application, which involves defining environment variables and configuring webhooks. The server code involves importing necessary packages, creating folders for storing images, and functions for generating and sending weather updates. The tutorial emphasizes the importance of JWT verification for security and offers insights into testing the application by accessing URLs for different cities. The guide encourages experimentation with developer tools and highlights further resources and community engagement opportunities through Vonage channels.

Benjamin Aronov, a developer advocate at Vonage, shares insights on using the Vonage Identity Insights API in Python to combat SIM swap fraud, a growing threat where attackers hijack phone numbers to intercept communications. The tutorial guides users through setting up a Vonage application, configuring a virtual environment, and writing a Python script to detect potential SIM swaps within a specified timeframe, using JWT for secure API authentication. The script allows for interactive command-line use, demonstrating how to identify SIM swap events with real-time feedback, making it a practical tool for developers to enhance mobile security. While the example uses a Virtual Operator for testing, it is applicable in production environments, and developers are encouraged to engage with the Vonage community for further support and updates.

Google has announced that starting November 1, 2025, all new and updated apps targeting Android 15+ devices must support 16 KB memory page sizes on 64-bit devices, a shift from the previously required 4 KB page sizes. This change, aimed at improving app startup times, power consumption, and overall system performance, affects apps utilizing native code, such as those using the Android NDK or third-party SDKs with native components like the Vonage Client SDK. Developers are advised to update their apps to ensure compatibility by adjusting native libraries and testing on devices with 16 KB pages, particularly for those using the Vonage Client SDK, which supports 16 KB page sizes from version 2.30.0. Additionally, Android 14 introduces a requirement for apps to use a Foreground Service (FGS) for audio recording, necessitating the implementation of a persistent notification to inform users about active recordings. This guidance ensures compliance with Android's new policies and enhances app stability on forthcoming devices.

Vonage has announced the release of the Video API v2.31.0, bringing new features and enhancements aimed at improving bandwidth management, session moderation, and telephony integration for more efficient video conferencing applications. The update introduces the ability to set a maximum bitrate for publishers, providing smoother experiences for users with limited bandwidth, and offers moderators the ability to forcefully disconnect participants to ensure a productive session environment. Additionally, new settings allow publishers to receive audio level updates even when muted, and platform-specific enhancements simplify integrating Android ConnectionService and iOS CallKit without requiring custom audio drivers. The release encourages developers to explore these updates through comprehensive documentation and community engagement opportunities provided by Vonage.

The Vonage Video API's new Audio Connector feature allows for seamless integration of real-time audio processing in video calls, enhancing functionalities like translation, transcription, and AI-powered interactions. By enabling the bidirectional audio flag, users can both send and receive audio in real time, which significantly expands the potential for applications such as AI-generated responses during conversations. An example use case is a video call with an AI travel advisor that can interact with users in real time, providing travel advice and booking assistance based on current data. This feature aims to improve user experience by enabling more dynamic and interactive audio exchanges, and a sample web application is available for users to explore its capabilities.

The tutorial outlines how to create a real-time interactive Rich Communication Services (RCS) experience using Node.js and the Vonage Messages API, aimed at enhancing user engagement for events like sports and music festivals. It highlights the use of RCS features such as suggested replies, rich cards, and carousels to create a dynamic user journey, exemplified by a football-themed application that allows users to vote on the "Man of the Match" and view related merchandise. The guide details the setup process, including configuring a Vonage API account, using ngrok to expose the local server, and structuring a Node.js project with modules for configuration and messaging templates. It provides a step-by-step approach to setting up an Express server to handle inbound webhooks and route messages based on user interaction, emphasizing modular code organization for easy adaptation. The tutorial concludes by encouraging further development of the user flow and integration with additional APIs, inviting developers to share their projects with the Vonage community.

The tutorial outlines how to send and open files over RCS using the Vonage Messages API and GitHub Codespaces, highlighting the advantages of RCS over SMS or MMS for sending high-quality files without strict size limits. It walks through setting up a development environment with GitHub Codespaces, installing necessary npm packages like dotenv and Vonage SDKs, and using environment variables to manage sensitive information such as API keys. The process involves creating a Vonage application, obtaining necessary credentials, and using a JavaScript file to send RCS messages with the Vonage Node.js library. The tutorial emphasizes best practices like using ngrok for real-time testing and suggests further enhancements like implementing rich card carousels to improve the user experience. It encourages engagement with the Vonage community and staying informed through various channels, including newsletters and social media platforms.

Yotam Luz, a Principal Data Scientist at Vonage, discusses the shift from human oversight to automation in AI, particularly in the context of Vonage AI's efforts to redesign speech-to-text (STT) systems using Large Language Models (LLMs). This shift is driven by the limitations of traditional benchmarking with human-generated "ground truth" and the need for scalable, unbiased, and context-aware evaluation methods. LLMs synthesize consensus transcriptions from multiple STT outputs, providing reliable reference transcriptions that allow for a fair comparison of model accuracy. The new pipeline demonstrates that LLM-generated references can deliver nearly identical Word Error Rates (WER) to human-labeled data, proving their robustness and scalability for benchmarking purposes. Despite higher error rates in human-labeled data, such references remain valuable for training, as demonstrated by the improved performance of models fine-tuned on this data. This approach accelerates benchmarking across new models and languages, eliminating the need for manual transcription while maintaining the benefits of human-labeled data for model development.

At the Carolina Code Conference, sponsored by Vonage, developers gathered in Greenville, South Carolina, to foster a sense of community and collaboration beyond just code. This inclusive event, marked by its unique setup of keeping everyone in the same room, allowed participants to connect and share experiences, making it feel more like a gathering of friends than a typical conference. Vonage, as the Platinum sponsor, engaged attendees with small gestures like giving away hats and headbands, which facilitated interactions and lowered barriers. The conference also included talks on topics like gamification and hosted social events, such as a happy hour at New Realm Brewery, which drew over 70 people despite a thunderstorm. Attendees like Justin Jones and Ben Link highlighted the power of forming genuine connections and friendships, illustrating the importance of community in Developer Relations (DevRel). Vonage emphasized its commitment to being an active member of the DevRel community, with the goal of creating spaces for people to connect and share ideas, thereby reinforcing the notion that meaningful connections are at the heart of the tech industry.

Vonage is enhancing developer experience by integrating CAMARA APIs directly into its products rather than offering them as standalone endpoints, allowing for seamless access to advanced network capabilities while maintaining consistency with existing Vonage APIs. This integration simplifies the complexity of working with multiple mobile operators, as Vonage manages the differences in CAMARA API implementations across countries, thus relieving developers from handling diverse operator-specific logic. Examples include embedding the CAMARA Number Verification API within the Verify API's Silent Authentication flow and incorporating SIM Swap detection into the Identity Insights API, which consolidates multiple identity insights into a single API call. This approach ensures faster integration, improved latency, and a unified authentication process, aligning with Vonage's commitment to supporting and contributing to the evolution of open standards like CAMARA.