{"version":1,"type":"story","url":"https://digestai.news/story/tencent-unveils-gander-model-that-talks-while-handling-background-task","json":"https://digestai.news/story/tencent-unveils-gander-model-that-talks-while-handling-background-task.json","markdown":"https://digestai.news/story/tencent-unveils-gander-model-that-talks-while-handling-background-task.md","slug":"tencent-unveils-gander-model-that-talks-while-handling-background-task","headline":"Tencent unveils Gander model that talks while handling background tasks","summary":"Tencent's Hunyuan Speech team introduced Gander, a model that can keep a real‑time conversation going while a separate \"brain\" component works on complex tasks. The architecture splits responsibilities: a fast \"cerebellum\" manages speech, image and text input second‑by‑second, and a swappable \"brain\" handles reasoning, code generation or other agent functions. Users may interrupt at any moment, and the system decides whether to listen, speak or pause without a dedicated voice‑activity detector.\n\nIn the Full‑Duplex‑Bench v3 evaluation covering 100 scenarios, Gander interrupted users in only 8 % of cases, compared with 13.5 % for OpenAI's GPT‑Realtime and about 48 % for the weakest competitor. The model lagged behind on overall task accuracy, especially in video and audio understanding, which the researchers attribute to training that favoured fluid conversation over precise perception. Gander was trained on roughly 2.7 million examples. Tencent plans to publish the model weights and training data after completing its open‑source release process, and a GitHub repository already hosts the code and demos.","keyPoints":["Gander interrupts users in only 8% of 100 Full‑Duplex‑Bench v3 scenarios, versus 13.5% for GPT‑Realtime.","Model processes speech, images and text simultaneously using a “cerebellum” for conversation and a swappable “brain” for complex tasks.","Tencent plans to open‑source Gander’s weights and training data; a GitHub repository already hosts the code."],"whyItMatters":"A conversational agent that can continue speaking while handling background reasoning reduces latency and improves user experience, addressing a core limitation of current voice assistants.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Tencent","OpenAI","Google","Anthropic","Sakana AI","Meta"],"models":["Gander","GPT‑Realtime","GPT‑5.6","Gemini Live","Claude Code","Hy3"],"people":[]},"firstPublishedAt":"2026-09-20T15:41:30Z","updatedAt":"2026-09-20T15:41:30Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"The Decoder","title":"Tencent's Gander aims to keep talking while it works in the background","url":"https://the-decoder.com/tencents-gander-aims-to-keep-talking-while-it-works-in-the-background","publishedAt":"2026-09-20T15:41:30Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Tencent unveils Gander model that talks while handling background tasks\", 20 September 2026, https://digestai.news/story/tencent-unveils-gander-model-that-talks-while-handling-background-task","publisher":"Digest AI","title":"Tencent unveils Gander model that talks while handling background tasks","datePublished":"2026-09-20T15:41:30Z","url":"https://digestai.news/story/tencent-unveils-gander-model-that-talks-while-handling-background-task"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}