OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API
OpenAI launched GPT-Realtime-2.1 and its mini version, cutting latency by 25% and adding a smaller reasoning model for voice agents.
- GPT-Realtime-2.1 and GPT-Realtime-2.1-mini are now available in OpenAI's API for low-latency voice agents.
- Latency improvements of at least 25% are achieved through enhanced caching in the new models.
- The mini variant offers a smaller reasoning model at the same price point as the previous mini model.
- WebRTC connectivity is now supported for smoother realtime voice interactions.
OpenAI has expanded its realtime API with two new models: GPT-Realtime-2.1 and GPT-Realtime-2.1-mini. The update focuses on reducing latency for voice-based agents, with the company reporting at least a 25% improvement in p95 latency through enhanced caching mechanisms. The mini variant is designed for cost-efficient reasoning in voice applications, maintaining the same pricing structure as its predecessor, gpt-realtime-mini.
The new models are part of OpenAI's push to improve realtime voice interactions, which are critical for applications like customer service bots, virtual assistants, and interactive voice response systems. Developers can now leverage WebRTC for seamless connectivity, enabling smoother and more responsive voice experiences. The updates reflect OpenAI's ongoing efforts to optimize performance while keeping costs accessible for broader adoption.
Source: OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API. Read the full piece at the source.
Enables faster, more responsive voice agents with reduced latency and cost-efficient mini models.
Improves customer experience in voice-based applications while maintaining competitive pricing.
Advances realtime AI voice technology for broader accessibility.
- p95 latency
- The 95th percentile latency, meaning 95% of requests are processed within this time.
- WebRTC
- A protocol for realtime communication over peer-to-peer connections, commonly used in voice and video applications.
AI ToolsThe AI Coding Tool You Use Is Now a Hiring Signal
AI ToolsMaster Local Fine-Tuning with "gemma-trainer"
From Hugging Face to Amazon SageMaker Studio in one click - Amazon Web Services (AWS)
AI ToolsTeaching models to forget: Selective unlearning with Amazon Nova
AI ToolsOur AI agents fabricated "done" five times in 17 days. Here is what actually reduced it.
The New Playbook for Enterprise AI Contracts - Emerj Artificial Intelligence Research
Emerj Research outlines a new framework for structuring enterprise AI contracts, focusing on risk management, compliance, and vendor accountability.
Police use of artificial intelligence grows as rules lag behind - Macomb Daily
Law enforcement agencies are increasingly deploying AI tools despite a lack of comprehensive regulations to govern their use.
RoboticsBritish Space Startup Launches Longevity Lab Into Orbit
A British space startup launched a lab into orbit to collect data on protein behavior linked to age-related diseases, aiming to train AI models for better predictions.
Business - Samsung Electronics profits surge 1,800% annually amid artificial intelligence spending boom - France 24
Samsung Electronics reported a staggering 1,800% annual profit surge, driven by soaring AI-related chip sales and infrastructure investments.
Stymied datacentre projects threaten global AI revolution - The Guardian
Major data center projects critical for AI growth face delays, threatening the global AI revolution.
Sam Altman Offers a Trojan Horse to American Taxpayers - Bloomberg.com
Sam Altman suggests the U.S. government invest in AI infrastructure to boost national competitiveness, framing it as a strategic public good.