Realtime AI

OpenAI says GPT-Live can listen while speaking using continuous audio, async reasoning and tool use, one-round-trip WebRTC startup, and async context compaction. Staff said the rebuilt stack removes a separate turn detector.

Google released Gemini Robotics 2, ER 2, and On-Device 2 for humanoid control, embodied reasoning, and on-device adaptation. Demos showed sub-second streaming and multi-robot task handoffs.

OpenAI released GPT-Live-Transcribe and GPT-Transcribe in the API for streaming and offline speech recognition. The launch adds context prompts, keywords, language hints, and WER gains, with Artificial Analysis reporting GPT-Transcribe at 3.31% AA-WER and $4.50 per 1,000 audio minutes.

OpenAI launched GPT-Live across paid ChatGPT Voice plans, with a free rollout in progress. The model can listen while speaking and delegate search or deeper reasoning asynchronously.

Grok Build added speech-to-text dictation for coding agents through /voice or Ctrl+Space. Try it to bring Grok-powered real-time voice input into CLI coding workflows.

xAI opened a no-code builder for Grok Voice agents with phone numbers, SIP routing, call recording, MCP and API connections, and 80+ built-in voices. The beta prices audio at $0.05 per minute, plus $0.01 per minute for xAI-provided telephony.

Vercel shipped realtime speech and transcription support in AI Gateway and AI SDK 7, then added Grok voice models through the same interface. The update puts voice agents on the same gateway, WebSocket, and AI SDK stack Vercel already uses for text models.

AssemblyAI’s Universal-3.5 Pro Realtime now carries forward the agent side of a conversation to improve live transcription. The release also ships multilingual realtime ASR features, and one early deployment said critical-utterance errors fell from 26% to 9%.

Vercel rolled out native WebSocket support so Node.js libraries like Socket.IO can run from CDN to Fluid. Existing sessions still reconnect at the 30-minute function limit, so teams should test long-lived connections before migrating.

LiveKit released Turn Detector v1 on Cloud and a smaller v1-mini bundled with its Agents SDKs for fast CPU inference. The model predicts end-of-turn directly from speech across 14 languages, changing interruption behavior and latency in voice agents.

Cartesia launched Sonic-3.5 for text-to-speech and Ink-2 for speech-to-text, calling them its new top streaming voice models. The release pairs low-latency voice-agent claims with 42-language support and immediate partner availability.

Zyphra released ZONOS2 under Apache 2.0 with 8B total parameters, 900M active, zero-shot voice cloning, 44.1 kHz DAC audio, and ZTTS1-Eval. The release includes open weights, inference code, and eval code, so teams can run real-time multilingual TTS without a hosted-only stack.

Google released Gemini 3.5 Live Translate for low-latency speech translation across 70+ languages in the Gemini Live API, AI Studio, and Google Translate. The same model is also heading to Google Meet in private preview for Workspace customers.

Artificial Analysis launched AA-WER Streaming to benchmark streaming speech-to-text models on accuracy and latency for voice agents. The first leaderboard puts Cartesia Ink-2 and ElevenLabs Scribe v2 on the price-latency frontier, so teams should compare cost against latency before choosing a model.

ElevenLabs launched Speech Engine, a layer that adds transcription, speech synthesis, turn-taking, and interruption handling on top of an existing chat agent. The release pairs SDKs, one-command setup, and 8¢-per-minute pricing for production voice agents.

Multiple users posted reproducible steps and videos showing Gemini app UI changes, Thinking Level rollout, and Fast mode or Canvas sessions that look like 3.2 or 3.5-class routing. This matters because Google appears to be testing new model paths and app surfaces in production ahead of I/O, though the exact model names remain unconfirmed.

Thinking Machines previewed interaction models that process audio, video, and text in 200 ms micro-turns, letting the system listen, speak, and react at the same time. The demos matter because the interaction loop is trained into the model instead of stitched together from separate speech and tool layers.

OpenAI added GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper to the Realtime API. The update gives voice agents live reasoning, translation, and transcription, but it remains API-only rather than part of ChatGPT voice mode.

Realtime TTS-2 ships as a low-latency speech model that conditions on prior audio turns, not just text, and claims sub-200 ms time-to-first-audio across 100+ languages. The release matters for voice-agent stacks because Replicate and LiveKit are already exposing it for real-time integration work.

Grok added standalone speech-to-text and text-to-speech APIs with WebSocket streaming, word timestamps, diarization, and support for 25-plus languages. Developers building realtime audio apps can now call Grok Voice infrastructure directly instead of wiring it through the app UI.

Alibaba launched Qwen3.5-Omni across Lite, Flash, Plus, and Plus-Realtime variants for native text, image, audio, and video understanding, plus realtime voice controls and script-level captioning. The family targets long multimodal sessions and live interaction, so watch the understanding-focused limits if you need media generation.

Mistral released open-weight Voxtral TTS with low-latency streaming, voice cloning, and cross-lingual adaptation, and vLLM Omni shipped day-0 support. Voice-agent teams should compare quality, latency, and serving cost against closed APIs.

Google launched Gemini 3.1 Flash Live in AI Studio, the API, and Gemini Live with stronger audio tool use, lower latency, and 128K context. Voice-agent teams should benchmark quality, latency, and thinking settings before switching.

KittenTTS released nano, micro, and mini ONNX TTS models sized for CPU-first deployment instead of GPU-heavy stacks. Voice-agent builders should benchmark both dependency weight and real-time latency before treating tiny size as enough.

Dreamverse paired Hao AI Lab's FastVideo stack with an interface for editing video scenes in a faster-than-playback loop, using quantization and fused kernels to keep latency below viewing time. The stack is interesting if you are building real-time multimodal generation or multi-user video serving.

xAI opened a Grok TTS API with five voices, inline controls for laughter and whispering, and multilingual streaming integrations that quickly landed in LiveKit and fal. Try it for voice products that need real-time playback, telephony formats, and hosted integration paths out of the box.

Artificial Analysis published results for NVIDIA's Nemotron 3 VoiceChat, putting the 12B model at the open-weight pareto frontier across conversational dynamics and speech reasoning. Consider it for open voice agents, but compare against proprietary systems that still lead the category by a wide margin.

Together AI launched a single-cloud stack for realtime voice agents that hosts Deepgram, Cartesia, MiniMax, and other voice components on one platform. Use it to cut latency and deployment overhead if you want one billing surface for production voice apps.