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.
Related guides (4)
Related events (8)
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.
Advancing voice intelligence with new models in the API
OpenAI is releasing new realtime voice models via its API with capabilities spanning reasoning, translation, and transcription. The announcement targets developers building voice-enabled applications and represents an expansion of OpenAI's voice intelligence offerings beyond the existing Realtime API. The models are positioned to enable more natural and intelligent voice experiences in production deployments.
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.
OpenAI Introduces Next-Generation Audio Models in the API
OpenAI is releasing new audio models via its API, including an updated text-to-speech model that accepts natural-language style instructions (e.g., 'talk like a sympathetic customer service agent'). This marks the first time developers can programmatically control speaking style through prompts rather than fixed voice presets. The release targets voice agent developers seeking finer-grained customization of synthesized speech.
Introducing the Realtime API
OpenAI has launched the Realtime API, enabling developers to build low-latency speech-to-speech experiences directly into their applications. The API provides native audio input and output without requiring separate transcription and text-to-speech steps. This represents a significant infrastructure offering for voice-enabled AI applications, moving beyond text-based API paradigms.
How OpenAI Delivers Low-Latency Voice AI at Scale
OpenAI published a technical overview of how it rebuilt its WebRTC stack to support real-time voice AI at global scale. The post covers infrastructure choices enabling low-latency audio delivery and conversational turn-taking. This represents a production-grade engineering disclosure about the systems underpinning OpenAI's voice products.
Mistral AI Releases Voxtral: Open-Weight Speech Understanding Models in 24B and 3B Sizes
Mistral AI has released Voxtral, a family of two open-weight speech understanding models (Voxtral Small at 24B and Voxtral Mini at 3B) under the Apache 2.0 license. Both models support long-form audio up to 30-40 minutes, native multilingual transcription, built-in Q&A and summarization, and function-calling directly from voice, built on the Mistral Small 3.1 language model backbone. Benchmarks show Voxtral outperforms Whisper large-v3 across all tasks and is competitive with GPT-4o mini and Gemini 2.5 Flash on audio understanding, while pricing starts at $0.001/minute via API. Models are available on Hugging Face and through Mistral's API, with a transcription-optimized variant (Voxtral Mini Transcribe) also offered.
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.