Anand B

Sun - Collaborative voice API for agents

by
Sun is a voice first AI model built specifically for real‑time collaborative voice interaction, not just one‑on‑one chat. ChatGPT Realtime and Gemini Live were built for one user talking to AI. Sun is built for collaboration — meetings, group calls, multi-agent debates, classrooms. One API, multi-speaker awareness, 10× the context window.

Add a comment

Replies

Best
Anand B
Maker
📌
Hey Product Hunt 👋 I'm Anand, co-founder of Sun (https://getsun.io). Every 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. 🌞 Sun is built for that: • Multi-speaker turn-taking • 10× the context window of ChatGPT Realtime and Gemini Live • Agent-aware barge-in (not just VAD) • Multi-agent in one room — run two AIs against each other on a real audio channel Today's PH offer: • Live playground — try it in your browser, no Credit Card → https://getsun.io • Live demo at https://demo.getsun.io Two things I'd love your help with: 1. Tell me where this breaks. We've stress-tested ~20 multi-speaker apps; we want yours to be #21. 2. What integrations would unlock you? LiveKit, Daily, Vonage, Twilio, custom WebRTC — drop a comment. Huge thanks to Anoop for hunting. Happy to answer anything in the comments today. 🌞
RegalDream

Does it mean that by using this, we can make our internal meeting agent talk in meetings about what is happening in meetings ? Like talking fireflies or otter ?

Anand B
Maker

@regaldreamtech Exactly — that's the core use case Sun was built for.


Fireflies and Otter listen silently. With Sun, you can build an agent that listens, knows who's saying what, and actually speaks up at the right moment — to summarize, answer a question, surface a related decision from earlier in the meeting, or even moderate.

Ashish Kushwaha

how does it know when to interrupt and when to not? Also, is there way to make it speak only when explicitly asked?

Anand B
Maker

@ashishkingdom Yes, you can actually give trigger words or names to the agent. The agent will then respond only when called with the name (and is asked a question), not when passively mentioned in a conversation. It also looks at voice activity to see if someone is actively speaking to avoid interrupting them.

Jaison

Does it take audio in or should we give transcribed text as inputs ?