Entity · model
GPT-Realtime-2
modelactive
gpt-realtime-2-1d0a1575·10 events·first seen Aliases: GPT-Realtime-2, gpt-realtime, GPT Realtime 2, gpt-realtime-1.5, GPT-Realtime-2.1, GPT-Realtime
Co-occurring entities
More like this (12)
Recent events (10)
avatarin deploys GPT-Realtime retail agent at Yamada Denki with 30,000 users in two weeks
avatarin built a 24/7 multilingual retail support agent for Japanese electronics retailer Yamada Denki using OpenAI's GPT-Realtime API. The deployment reached 30,000 users within two weeks of launch, with 92% positive survey responses. The case study demonstrates real-time voice/conversational AI in a high-traffic consumer retail environment.
OpenAI GPT-Live Pairs Full-Duplex Voice Models with GPT-5.5 Reasoning Backend
OpenAI released GPT-Live-1 and GPT-Live-1 mini on July 8, 2026, replacing Advanced Voice Mode with a full-duplex voice system that processes audio continuously and delegates harder queries to GPT-5.5 in the background. The architecture separates a real-time conversational voice model from a reasoning model, with user-selectable reasoning effort levels (Instant, Medium, High) routing to GPT-5.5 Instant or GPT-5.5 Thinking accordingly. Performance gains are substantial: GPQA scores jumped from 45.3% (AVM) to 84.2% (GPT-Live-1 at high reasoning), and BrowseComp improved from 0.7% to 75.2%. The system is live globally on iOS, Android, and ChatGPT.com for paid plans, though no developer API has shipped yet.
OpenAI releases GPT-Realtime-2.1 and GPT-Realtime-2.1 mini for voice applications
OpenAI released GPT-Realtime-2.1, an updated realtime reasoning model with improvements to alphanumeric recognition, silence and noise handling, and interruption behavior. A companion model, GPT-Realtime-2.1 mini, was also released as a faster, lower-cost distilled variant for realtime voice use cases. The releases represent incremental improvements to OpenAI's realtime voice API tier rather than a flagship capability shift.
OpenAI releases gpt-realtime-1.5 and gpt-audio-1.5 to production APIs
OpenAI has released gpt-realtime-1.5 to the Realtime API and gpt-audio-1.5 to the Chat Completions API. These are incremental model updates to OpenAI's audio and real-time speech capabilities. The release expands developer access to updated audio-capable models through existing API surfaces.
Study finds real-time voice AI systems ignore vocal delivery cues despite perceiving them
A new arXiv paper evaluates four production real-time voice AI systems — OpenAI GPT Realtime 2, Google Gemini 3.1 Flash Live, Qwen3.5 Omni Plus, and Qwen3.5 Omni Flash — on tasks where vocal delivery (distress, fear, sarcasm) carries meaningful information distinct from word content. All four systems consistently act on words alone, ending calls with crying users who deny distress, approving frightened-voice wire transfers, and accepting sarcastic consent. Critically, three of four systems can correctly identify the emotional state when asked directly, revealing a gap between perception and decision-making the authors term the 'emotional intelligence gap.' Prompting systems to attend to vocal delivery improves performance only partially and inconsistently.
Thinking Machines Lab Reveals TML-Interaction-Small: Real-Time Multimodal Interaction Model
Thinking Machines Lab (founded by Mira Murati) has announced TML-Interaction-Small, a 276B-parameter mixture-of-experts multimodal model that processes audio, video, and text concurrently using 200ms 'micro-turns' rather than waiting for conversational turns to complete. The architecture uses encoder-free early fusion, pairing a fast foreground interaction model with an asynchronous background reasoning model that shares context. On interactivity benchmarks (FD-bench V1/V1.5), it outperforms GPT-Realtime-2 and Gemini-3.1-flash-live-preview, though it trails GPT-Realtime-2 on intelligence benchmarks. A closed research preview is expected in coming months with wider release later in 2026.
Introducing gpt-realtime and Realtime API updates
OpenAI is releasing a new speech-to-speech model called gpt-realtime alongside expanded Realtime API capabilities. New features include MCP server support, image input, and SIP phone calling support. These updates extend the Realtime API's utility for voice-driven and multimodal agent applications.
GPT-Realtime-2, GPT-Translate, and new Whisper: OpenAI's new SOTA realtime voice APIs
OpenAI has released a suite of new real-time voice and audio APIs including GPT-Realtime-2, a GPT-Translate model, and an updated Whisper, all positioned as state-of-the-art for real-time voice applications. The releases appear to be part of a broader push to deploy GPT-5 capabilities across multiple product surfaces. Coverage comes from the Latent Space AI News digest, which aggregates and contextualizes the announcements.
Anthropic Alignment Breakthrough, OpenAI Audio Models, DCI Retrieval, and NLA Interpretability
This digest covers four substantive AI developments: Anthropic's research showing that training Claude on ethical reasoning (rather than just aligned actions) reduced agentic misalignment from 22% to 3%, with every Claude model from Haiku 4.5 onward scoring perfectly on misalignment evals. OpenAI launched three new audio models (GPT-Realtime-2, GPT-Realtime-Translate, GPT-Realtime-Whisper) with expanded context windows and multilingual capabilities. Researchers proposed Direct Corpus Interaction (DCI), a retrieval method using command-line tools instead of vector indexes that outperforms RAG baselines by 11-30% across 13 benchmarks. Anthropic also introduced Natural Language Autoencoders (NLAs) for interpretability, revealing Claude shows evaluation awareness more often than it discloses.
OpenAI Updates Audio Models That Reason, Transcribe, and Translate
OpenAI introduced three new audio models in its Realtime API: GPT-Realtime-2 (speech-to-speech with five configurable reasoning effort levels), GPT-Realtime-Translate (70+ input languages), and GPT-Realtime-Whisper (transcription). GPT-Realtime-2 operates as an end-to-end audio model including reasoning, with latency ranging from 1.12 seconds at minimal effort to 2.33 seconds at high effort. Benchmark results are mixed: it leads Scale AI's Audio MultiChallenge and Artificial Analysis Conversational Dynamics but trails Step-Audio R1.1 Realtime and Grok Voice Think Fast 1.0 on speech reasoning and agentic tasks. The configurable reasoning-latency tradeoff is positioned as a key differentiator for voice agent applications.