Radar / AI models / Qwen-Audio-3.1-Realtime-Plus

Qwen-Audio-3.1-Realtime-Plus: full-duplex voice model with think-act-speak loop

Alibaba Qwen's real-time duplex speech model (text+audio in/out) that reasons, uses tools, and decides when to speak mid-conversation, with function calling and web search.

new launchmodels · frontierJEV traction 0.52added 2026-09-30
Open Qwen-Audio-3.1-Realtime-Plus →View on the radar

Why it matters

One of the first Chinese open-API full-duplex voice models with explicit think/act/speak reasoning and GRPO-trained tool use; 262K context at $6.4/M audio-input tokens vs $32 for OpenAI's realtime model.

What you could build with it

A call-center SaaS team could prototype a bilingual voice agent that interrupts, backchannels, and calls tools mid-conversation - at roughly one-fifth the audio-token cost of Western realtime APIs.

Does it hold up?

Too early to judge - API docs live, no independent benchmarks or production deployments reported yet.

Learn more

official docs →

First spotted on article: source.

More AI models

ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.