OpenAI Realtime API

Voice & Multimodal

Speech-to-speech API for building low-latency voice agents over WebRTC or WebSockets.

🌐 Visit website ↗

🔗 Similar tools

GPT-Live-1 / GPT-Live-1 mini

GPT-Live-1 is OpenAI's full-duplex conversational voice model, released July 8, 2026, as t…

Models & AI Labs
OpenYabby ★ 127

OpenYabby is an open-source macOS voice-driven multi-agent orchestrator that combines the …
Cartesia

Cartesia provides ultra-low-latency voice AI designed for real-time conversational agents,…
Tencent Hunyuan Hy3

Tencent Hunyuan Hy3 is an open-source (Apache 2.0) Mixture-of-Experts model with 295B tota…

Research & Resources
Qwen Code ★ 27.7k

Qwen Code is an open-source terminal coding agent from Alibaba's Qwen team, supporting age…

Coding Agents
Pipecat ★ 15.2k

Pipecat is an open-source framework (BSD-2-Clause) for building voice and multimodal conve…