[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-magenta-realtime-2-google-macbook-music":3,"news-related-829da3b0-1bfd-4fc1-9092-e265106a5696":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"829da3b0-1bfd-4fc1-9092-e265106a5696","Magenta RealTime 2 开源：Google 把实时音乐生成装进 MacBook","2026 年 6 月 4 日，Google DeepMind 的 Magenta 团队正式开源了 Magenta RealTime 2（MRT2）。它和\"prompt→成曲\"的传统工具截然不同：模型只有 2.4B 参数，却能以约 200ms 的端到端控制延迟持续输出 48kHz 立体声音频，并同时接受文本、音频示例与 MIDI 三种信号\"领航\"——创作者按住一个和弦，模型就在背后实时补出整支乐队，这恰恰是过去所有文本生成音乐模型都做不到的事。\n\n## 工程上做了三件实事\n\n- **全量开源**：权重 CC BY 4.0、代码 Apache 2.0；\n- **原生 Apple Silicon**：借助 MLX 后端与 C++ 推理引擎在 MacBook 上跑出实时流；其中 mrt2_small（230M 参数）从 M1 Air 起即可实时，mrt2_base 需要 M2 Pro 及以上；\n- **可即插即用**：官方 AUv3 插件与 Jam、Collider 等独立应用，让模型直接嵌入主流 DAW 工作流，把\"会演奏的模型\"第一次以乐器的形态交到音乐人手里。\n\n## 双轨策略值得玩味\n\nGoogle 同时维持\"开源权重 + 闭源 Lyria RealTime API\"：本地权重服务音乐人和研究者，云端 API 服务消费级产品 MusicFX DJ Mode 等。这种\"研究开放、商业封闭\"的组合，本质上把模型本身变成了社区生态的底盘，把 API 当作货币化的入口。\n\nHugging Face 和 GitHub 仓库上线不到 24 小时，社区已经做出手势控制 MIDI 的即兴 demo——DeepMind 研究员 Jesse Engel 在飞机上无网络、靠 MacBook 摄像头手势指挥 MRT2 演奏，被同行称为\"Oh, I'm living in the future\"。\n\n当下真正稀缺的不是\"模型能不能写歌\"，而是\"模型能不能和你一起演奏\"。音乐生成的\"工具时代\"，确实要过去了。","https:\u002F\u002Fmagenta.withgoogle.com\u002Fmagenta-realtime-2","35ce748f-48b7-4638-88ef-effa57a7e749",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"8cf7490f-2449-4ba7-be19-61befa0d92b4","google",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b1853a5a-d940-42b7-94f9-0488ee3f2cf7","new-model",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"7b9bbf73-ffbc-4f47-9ec1-d6e3ee056ad0","en","Magenta RealTime 2: real-time music generation on a MacBook","On June 4, 2026, Google DeepMind's Magenta team officially open-sourced Magenta RealTime 2 (MRT2). It is fundamentally different from the \"prompt → song\" tools of the past: the model has only 2.4B parameters, yet can continuously output 48kHz stereo audio with end-to-end control latency of about 200ms, while simultaneously accepting text, audio examples, and MIDI signals as \"navigation\" — a creator holds a chord, and the model fills in the entire band live in the background, which is exactly what all previous text-to-music models could not do.\n\n## Three engineering deliverables\n\n- **Fully open-sourced**: weights CC BY 4.0, code Apache 2.0\n- **Native Apple Silicon**: with the MLX backend and C++ inference engine, runs real-time on MacBook; the mrt2_small (230M parameters) runs real-time from M1 Air, mrt2_base needs M2 Pro and above\n- **Plug-and-play**: the official AUv3 plug-in and independent apps like Jam and Collider let the model be embedded directly into mainstream DAW workflows, putting \"an instrument that can play\" into musicians' hands for the first time\n\n## The dual-track strategy is worth pondering\n\nGoogle simultaneously maintains \"open-source weights + closed-source Lyria RealTime API\": local weights serve musicians and researchers, cloud API serves consumer products like MusicFX DJ Mode. This \"research open, business closed\" combination essentially turns the model itself into the bedrock of the community ecosystem, and the API into the monetization gateway.\n\nLess than 24 hours after Hugging Face and the GitHub repo went up, the community had already built a gesture-controlled MIDI improvisation demo — DeepMind researcher Jesse Engel used his MacBook camera to gesture-direct MRT2 to play on a plane offline, and a peer called it \"Oh, I'm living in the future.\"\n\nWhat's really scarce today isn't \"can the model write a song,\" but \"can the model play with you.\" The \"tool era\" of music generation is indeed ending.","magenta-realtime-2-google-macbook-music","2026-06-09T22:00:00Z","2026-06-09T22:11:20.540577Z","2026-08-19T02:08:40.142862Z",true,"agent",112,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"dccdd14b-babe-4883-b0ec-0cf5b1d85018","MiniMax Music 3.0 把「5 分钟完整歌曲」开源:Hybrid-LM + Flow-VAE 让音乐生成跨过录音室门槛","minimax-music-3-5min-song-open-source","2026-08-15T00:00:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"1d80585e-c797-4aa1-ac68-ef87334d5d0c","PLaMo 3.0 Prime 正式发布：PFN 把「日语实战」做成日本国产 LLM 的差异化战场","plamo-3-0-prime-pfn-japanese-domestic","2026-06-24T08:15:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"97a4f24e-c65b-4e95-b9ed-b05997d88af2","Qwen3.6-35B-A3B发布：开源大模型的效率革命","qwen-3-6-35b-a3b-open-source-coding-262k","2026-04-25T02:05:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"2203a8bc-acb4-49b6-b3d1-ab8622d24c0d","Lyria 3 Pro 把生成音乐拉到 3 分钟：结构化作曲、ProducerAI 代理化协作与全链路 SynthID","lyria-3-pro-google-deepmind-3-min-structured","2026-03-25T16:00:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"f6e4aab0-7693-4c2c-bb66-c1641fc2cc3e","Ox Alpha 谜底揭晓:智谱 GLM-5.3-Flash,MIT 开源 320B MoE","ox-alpha-glm-5-3-flash-reveal","2026-08-27T13:30:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"804ab59a-a8d6-4b61-bf74-8f6f2bdae83c","智谱把 Flash 做成一件正经事:一次说清 GLM-5.3-Flash 的架构和 benchmark 真相","glm-5-3-flash-hybrid-attention-architecture","2026-08-27T08:00:00+00:00"]