Real-time voice refers to low-latency spoken conversational artificial intelligence interaction technologies. Truncated covers latency benchmarks, speech synthesis models, audio quality improvements and application integrations.
AI-generated summary OpenAI plans to discontinue the Advanced and Standard voice options in ChatGPT on December 11, 2026, making GPT-Live the platform default. OpenAI says nearly all voice users have switched to GPT-Live since July, though live video and screen-sharing will temporarily keep using Advanced voice.
AI-generated summary Fish Audio has launched Live 3, which is a duplex voice AI model built for AI agents that operate phone calls. The model can distinguish pauses in phone numbers from the end of a question and has a reaction speed under 200 milliseconds.
AI-generated summary Cartesia introduces Joyce as a researcher working on the speech-to-speech team. Cartesia shares a personal story about the researcher through a published link.
AI-generated summary OpenRouter Blog published a tutorial on building a voice AI restaurant booking agent in Python that transcribes callers, uses tools to check availability, and converts responses into speech. OpenRouter Blog states that across 12 test turns, the median server-side time to first audio was 1.9 seconds, with text-to-speech accounting for roughly 90% of the measured model cost.
AI-generated summary Runway Labs designer and prototyper Ryan Stephen explores how real-time video could change learning, creation, and collaboration. The inside view video examines concepts related to video that responds to users.
AI-generated summary Nuance Labs has launched a free artificial intelligence character named Emma that allows users to engage in video chats. The character is built on the new Nuplex model, which Nuance Labs states matched human response times in eighty-nine percent of tests.
AI-generated summary Cartesia built a claims intake agent on Cartesia Managed Agents to answer coverage questions and make live tool calls. Cartesia says the voice agent stays empathetic throughout the interaction and invites users to a webinar next Tuesday.
AI-generated summary Cursor and Google have introduced new two-way voice features for their coding agents to let developers speak with the software while it works. Google added Voice mode to Antigravity using Gemini Live, while Cursor released Voice Chat with Agents powered by Grok Voice.
AI-generated summary Cartesia is bringing Coffee Cartesia to Hudson River Park on Thursday, 11/12, from 8am to 12pm with free coffee and cocoa. Cartesia says a voice agent barista will take orders so visitors can experience real-time voice AI.
AI-generated summary ElevenLabs announced the launch of ElevenAgents Campaign Manager to help outbound teams manage sales, retention, patient care, collections, customer service, and recruiting operations. ElevenLabs says the new tool allows agents to call contacts during set hours, carry context between interactions, and run campaigns over phone calls and WhatsApp.
AI-generated summary William Imoh explains how he used Codex and GPT-Live to build the real-time voice app Mural for iOS and Android. The founder also discusses using Grok to create a Lord of the Rings themed bot fellowship to help manage his team.
AI-generated summary Microsoft has filed a patent for generative artificial intelligence that can alter content in livestreams in real time by listening for certain words and replacing them. Microsoft says the technology is intended for cleaning up and translating broadcasts, though the filing has raised concerns regarding potential misinformation.
AI-generated summary ElevenLabs details voice AI infrastructure layers including speech recognition, turn-taking, and large language models for voice agents. ElevenLabs says its ElevenAgents uses Scribe v2 Realtime for speech transcription and supports Custom and Realtime modes.
AI-generated summary Voxtral 3 features end-of-turn detection to help developers identify when a user has finished speaking. According to @MistralAI, the tool makes it easier to build responsive voice interactions.
AI-generated summary Forbes published an article by technology executive and software architect Alexandro Picolini discussing the engineering challenges of moving voice AI from a controlled demo environment into production. The author notes that real telephone operations face issues such as degraded audio quality, background noise, and latency that do not appear in simple demonstrations.
AI-generated summary ElevenLabs has released the new ElevenAgents Unity SDK to connect game scenes to a voice agent. The SDK runs in the Editor, desktop builds, and WebGL, with support for iOS, Android, and XR in beta.
AI-generated summary Google is developing an offline mode for Gemini Live that requires an active data connection for the initial setup process. Code discovered in the latest Google app indicates that the offline experience will feature a reduced set of capabilities and limited features.
AI-generated summary Meta announced that Muse Voice is now available to users in the U.S. for video chatting and calling with the consumer AI agent. The feature uses Muse Realtime Avatar and Muse Realtime Voice technology to power an animated character that interacts with users.
AI-generated summary GPT-Live 1 is OpenAI’s voice model that listens and speaks at the same time and shipped in ChatGPT Voice on July 8, 2026. Developers can use the gpt-live-1 API to delegate reasoning and tool tasks to text models while maintaining a continuous voice conversation.
AI-generated summary Meta announces the rollout of real-time voice conversations and expressive avatars in the Muse app on mobile, web, and Mac in the US. Meta says the new features allow users to talk through ideas, practice for interviews, and choose from hundreds of different voices.
The top AI news in your email delivered each morning. Choose categories