Developer Paul Kulak released Barnaby, a self-hosted Matrix chat server and AI agent that deploys from a domain, an SSH key, and an OpenRouter API key via one command. Barnaby Home bundles the tuwunel…
Developer Sainigurnoor511 released Frontdesk.ai, an open-source, self-hosted AI receptionist published under the Apache-2.0 license at github.com/Sainigurnoor511/frontdesk-ai, as an independent take o…
Owll Translator, a real-time interpretation app, cut perceived latency in its Flutter client by prewarming session connections, treating preloaded session grants as single-use, and streaming partial r…
A LiveKit voice agent named Alex, built as a carrier sales rep for a fictional freight brokerage, cut the margin it gave away in rate negotiations from an average of 40% in its first version to 14% in…
Microsoft AI voice models are now available in LiveKit Agents through an official Microsoft AI text-to-speech plugin, giving developers a documented way to use expressive MAI voices such as MAI-Voice-…
Axionry Engineering reported that its AI phone interviewer runs on a custom LiveKit pipeline at about 2.5¢ per minute, down from roughly 10¢ per minute on a managed voice platform, a 75% cost cut. The…
Simple AI introduced Tango, an audio-native end-of-turn model that in production lands its end-of-turn decision a median 300ms before a conventional voice-activity detector would detect a pause, measu…
Calnode launched as an Apache-2.0 self-hosted Calendly alternative distributed as a single Go 1.26 static binary with an embedded SQLite database, requiring no Redis, Postgres, or separate API server.…
Synthesia launched its Interactive Avatar API today for Enterprise customers, letting developers embed real-time, photorealistic, lip-synced avatars into web products using the company's new Express-3…
Zizka-ai released ZizkaDB, an open-source, self-hosted audit trail for AI agents that logs each agent step with a parent_id so teams can trace a tool call or response back to its root cause. The stack…
Google released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking in its API and Google AI Studio, adding native speech-to-speech capability for voice-first agents. Gemini 3.8 Live Extended Thinki…
Synthesia launched Interactive Avatars, a generally available plugin that attaches to a LiveKit Agent and renders a real-time talking avatar as a video participant in a web or mobile app, priced at $0…
Google released new Gemini Live models in the Gemini API and Google AI Studio, including Gemini 3.8 Live and 3.8 Live Extended Thinking, which the company says rank first on Artificial Analysis' Speec…
Google introduced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, two models built for near real-time reasoning and production-ready voice agents. Gemini 3.8 Live Extended Thinking took the #1 …
An AI developer is seeking production-grade advice on designing a real-time voice AI architecture that achieves first-token latency of roughly 500 ms or less while remaining cost-effective and scalabl…
A developer built an AI Voice Learning Assistant during Murf AI's 10 Days of Voice Agents — VoiceForBharat Edition, under the Learning & Literacy track. The system uses LiveKit, Deepgram Nova-3, Googl…
Runway's GWM Worlds 2, released September 3, 2026, is the first general world model to generate real-time interactive video at 720p/24fps with synchronized 48kHz audio, supporting arbitrary actions an…
Dograh, a self-hostable voice agent platform positioned as an open-source alternative to Vapi and Retell, is now available under a BSD-2-Clause license, enabling teams in regulated industries to keep …
A developer built Maya, a real-time voice AI receptionist for a fictional Bengaluru clinic, using LiveKit, Groq, and Cartesia to handle appointment bookings with sub-second latency. The project showca…
Speaker diarization, the automatic assignment of speech segments to individual speakers in an audio stream, is being positioned as a core requirement for AI voice agents handling business telephony, a…