best ai voice agent 2026

@miyaura(Miyaura)Using MCP Server Tools in Voice Live - Differences from Function Calling and Parallel Tool CallsAzureMicrosoftFoundryVoiceLiveAPIMCPAI0Last updated at 2026-11-10Posted at 2026-11-10 Trying MCP Server Tools in Voice Live I wanted a voice-conversation agent to be able to look things up using external tools, so I tried it with the Voice Live API. The Voice Live API is an API for building agents that converse using voice. There are two ways to

@miyaura(Miyaura)Improve Voice Live Audio Input Quality — How to Choose Noise Suppression, Echo Cancellation, and Live-Reference AECAzureMicrosoftFoundryVoiceLiveAPIdotnetAI0Last updated at 2026-11-10Posted at 2026-11-10 Introduction In voice agents, the quality of the sound entering the microphone matters more than you might expect. Noise and audio bleeding in from the speaker can throw off not only speech recognition accuracy, but also speech-segment det

@miyaura(Miyaura)Changes in Voice Live SDK 1.2.0 and API 2026-07-15 GA - Classifying Features Without Types in the SDKAzureMicrosoftFoundryVoiceLiveAPIdotnetAI0Last updated at 2026-11-10Posted at 2026-11-10 A Look at What Changed in Voice Live SDK 1.2.0 Microsoft Foundry's Voice Live API is an API for building agents that converse using voice. Its .NET SDK (Azure.AI.VoiceLive) had reached version 1.2.0, so I wanted to take a look at the available features

@miyaura(Miyaura)Calling Foundry Agents as Tools in Voice Live - How to Use the chat-supervisor Pattern and Choose a Front-End ModelAzureMicrosoftFoundryVoiceLiveAPIAIAgentAITAG28@@TAG30@@0TAG34@@Last updated at 2026-11-10Posted at 2026-11-10

The startup was founded by Carlo Edoardo Ferraris, who previously founded tech accessories company Rolling Square. After years of building consumer hardware, he became convinced that rapidly advancing AI needed a new kind of interface that lets people ask for what they want the way they’d ask a person. The idea behind Interface is to help people look up from their phones while getting everyday tasks done more quickly and naturally. At launch, the ring will

The companies didn’t disclose the deal amount but said that they will keep Pipecat open source. For the uninitiated, Pipecat is a framework that manages voice and video streams along with other pieces in the pipeline, like speech-to-text (STT), large language models (LLMs), and text-to-speech (TTS) models while reducing latency. Its maker, Daily, provides hosted infrastructure for voice and video calls of any kind. With Pipecat, Deepgram will likely gain a

Anthropic takes on Grok Bot, Meta's Muse, and OpenAI's Dots with its always-on agent "Claude Duet" Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner Oct 22, 2026 Anthropic / GPT-Image-2 prompted by THE DECODER Key Points Anthropic has released a preview of "Claude Duet," an app where an AI agent handles tasks for the user in the background. The app runs on cloud computers and connects to outside services like Gmail, Slack, and Stripe.

Every week there is a new model or a tool release that claims to sound human and converse like one. However, in reality, that might not be the case. Enterprise voice AI platform PolyAI’s CTO Shawn Wen thinks that despite the release of full-duplex models — which can speak while listening to you — voice AI hasn’t had its “ChatGPT moment” yet. “We have reached the milestone of developing full-duplex models. The next challenge is to make reasoning very fast,

Zhidongxi (WeChat official account: zhidxcom) Author | Yang Jingli Editor | Li Shuiqing Zhidongxi reported on November 5 that Alibaba released the “Alibaba AI for Good Action Report 2026” today. The report centers on “Full-stack AI, collaborating for good” and proposes that AI development must simultaneously meet three conditions: “socially acceptable, environmentally sustainable, and economically sustainable”. The report’s AI-for-Good initiatives cover he