Sun launches collaborative voice API for multi-speaker real-time interactions
By
John
Summary
Sun is a collaborative voice API designed for multi-speaker real-time interactions, unlike existing voice APIs (OpenAI Realtime, Gemini Live, Hume) that only support one-on-one conversations. It features multi-speaker turn-taking, a context window 10× larger than competitors, agent-aware barge-in, and multi-agent support — making it suitable for sales calls, classroom debates, group brainstorms, and multi-agent workflows.
Source
Key quotes
· 3 pulledEvery realtime voice API today — OpenAI Realtime, Gemini Live, Hume — was built for one user talking to one AI.
That breaks the moment a third voice enters the room.
Sales calls, classroom debates, multi-agent workflows, group brainstorms — they all need voice infra that knows who's talking, when to interrupt, and how to let three speakers share a turn.
You might also wanna read
VoiceAI: A Developer's Learning Path for Building Real-Time Voice Agents
A curated, developer-friendly learning path for building real-time voice AI agents, covering the full stack from speech-to-text foundations
Realtime solar system
OpenAI launches three new audio models for real-time voice applications in the API
OpenAI is introducing three new audio models in its API that enable developers to build more natural, intelligent, and real-time voice appli

Voice agents guide
Building a Sub-500ms Latency Voice Agent: Technical Architecture and Implementation
Nick Tikhonov shares his technical journey building a sub-500ms latency voice agent from scratch, detailing the challenges of achieving real
How OpenAI rebuilt its WebRTC stack for low-latency voice AI at scale
OpenAI rearchitected its WebRTC stack to address three key constraints for real-time voice AI: low-latency audio delivery, global scale, and

Comments
Sign in to join the conversation.
No comments yet. Be the first.