LiveKit and Wavix have integrated to enable real phone calls within LiveKit-powered applications. The integration allows developers to handle inbound and outbound calls, with features like call transf…
A developer running a voice AI sales training platform intentionally slowed down their voice agent's pipeline to fix an interruption problem. The pipeline's p95 latency of 880 ms was fast enough that …
TrueVoice HQ has built a real-time AI interview analysis pipeline using LiveKit, Deepgram, and Grok that scores live video interviews chunk by chunk, providing interviewers with live authenticity sign…
A developer explains how to give voice AI agents built on LiveKit, Vapi, or Retell a legitimate Indian (+91) phone number, addressing the lack of developer-friendly tooling from Indian telecom provide…
AlphaAvatar v0.6.4, an open-source self-hostable runtime for realtime multimodal AI assistants, has been released with a new architecture separating core perception, RTC adapters, and agent orchestrat…
Calnode, a self-hostable open-source scheduling app combining booking, video calls, and recording in a single Go binary, launched with AI-native conversational booking and an MCP server for agent inte…
XAI launched the Grok Voice Agent Builder in beta on July 1, featuring a single speech-to-speech model that replaces the traditional three-API voice stack. The platform offers sub-700ms latency and co…
LiveKit released a guide on building a HIPAA-compliant voice agent that keeps protected health information (PHI) within a self-hosted boundary, ensuring data never leaves the organization's infrastruc…
Hail.so launches an open-source MCP server, CLI, and API that unifies email, SMS, and phone call capabilities under a single interface, packaging Twilio, AWS SES, LiveKit, ElevenLabs, Cartesia, and LL…
Sakshi Kesarwani built BazaarLive, a live video auction platform for India's $16 billion collectibles market, during the H0 Hackathon. The platform uses LiveKit for streaming, WebSocket bidding with s…
LiveKit released two end-of-turn detection models that process speech directly instead of relying on transcripts, fusing semantic and acoustic understanding. The v1 model achieves top results across 1…
The San Francisco Voice Company launched a real-time alert system for video and audio applications, designed for teams handling over 10,000 calls per day. The platform detects acoustic features beyond…
LiveKit released eot-bench, an open benchmark suite for end-of-turn detection in voice AI, along with the first open dataset of real human-to-agent conversations in 14 languages. The benchmark evaluat…
AGI House, the Hillsborough, California community founded by Rocky Yu in 2023, is shifting its programming toward AI agents and automation with a series of build events in San Francisco, including a J…
LiveKit has released a new integration with OpenTelemetry and SigNoz that enables developers to monitor and observe voice agent applications in real time. The setup allows teams to track latency, erro…
Fluxer's public beta roadmap has been overhauled since January, with the canary client now far ahead of the stable release and native mobile apps entering testing. The hosted instance scaled rapidly a…
Prodinit, operating a healthcare scheduling platform at over 2,000 calls per day, has identified that sub-300ms end-to-end latency is the critical threshold for production voice AI agents, with the la…