Researchers from Tencent’s Hunyuan Speech team and partner universities introduced Gander, an AI model designed to maintain real-time conversational flow while executing background reasoning tasks. To balance rapid conversational responses with heavy compute demands, Gander splits operations into two units: a ‘cerebellum’ for managing continuous voice interaction and a modular ‘brain’ for executing multi-step tasks like coding or search.
The system evaluates inputs in one-second segments, allowing users to interrupt or receive spontaneous status updates without dedicated speech detection modules. In benchmarks on Full-Duplex-Bench v3, Gander demonstrated superior conversational timing compared to systems like GPT-Realtime and Gemini Live. However, researchers noted small trade-offs in overall task accuracy and precise visual perception, which they attribute to training optimization favoring fluid dialogue.
The system can swap its background ‘brain’ with external model endpoints such as Claude Code or OpenAI models. Tencent plans to open-source Gander’s weights, code, and training dataset upon completing internal review processes.
Why it matters
Offers a modular design pattern for real-time AI voice agents executing background compute tasks.
Decouples latency-sensitive speech interaction from heavy reasoning backends, allowing drop-in upgrades of underlying LLMs.
Source: the-decoder.com
