Genspark launches Media Studio video-agent workbench with 70+ models from 20+ vendors
Genspark has officially launched Media Studio, an all-in-one video-agent workbench that integrates over 70 model versions from more than 20 vendors. It offers three LLM 'director' options (DeepSeek V4.1 Flash, Claude Opus 5.5, Claude Fable 5.1) and uses models like Seedance 2.5, Kling, Veo for video, GPT Image and Nano Banana for images, and ElevenLabs for audio. A promotional discount halves credit consumption for Plus and Pro members from Oct 27 to Nov 4, 2026.
Coverage timeline
量子位量子位
奥特曼和Dario同台唱rap！Genspark新视频Agent上线，零基础也能拍短剧 听雨 2026-10-29 14:53:19 来源： 量子位 All in one、任何人都能用 Genspark 的视频Agent工作台， Genspark Media Studio ，正式发布了！ 这次，它把一批前沿模型拉到了一起，组了个AI剧组。 负责当「导演」的大语言模型有三档可选：DeepSeek V4.1 Flash、Claude Opus 5.5，以及Claude Fable 5.1。 是的，在这里面甚至能用上Fable 5.1…… 说实话因为某些众所周知的原因，我已经很久没有用到了。。。 具体干活的模型包括：Seedance 2.5、Kling、Veo负责生成视频，GPT Image、Nano Banana负责图像，ElevenLabs等音频模型负责声音。 总共接入了20多家厂商的70多个模型版本。 而且最近还打折！ 北京时间10月27日18:00至11月4日18:00，Plus和Pro会员在Media Studio里的积分消耗 打五折 ，规划、图片、视频、音频和3D生成都算在内。 6G冲浪的量子位也是第一时间拿到了实测资格。 我们直接走起～ 实测Genspark Media Studio：奥特曼唱rap、拍商战短剧，都安排上了 一键get同款 在首页的Genspark Magic分区里，有很多爆款视频模版，点击即可一键做同款。 我精心挑选了一个rap视频，把奥特曼和Dario的照片传了上去。 美股IPO两兄弟，就是你们了！ 但有个问题我没考虑到，如果直接上传真人图片，会被视频模型拦截。 Genspark还提醒我开拍前要确认版权问题，怪细心的。 系统再次提示使用半写实版还是卡通版，我选择了半写实版（赌一把），都确定后，它就开始工作了。 Agent调用了Seedance 2.5，虽然提示8-14分钟出片，但我体感大概两三分钟（？）片子就做出来了。 第一版出来的视频没有配乐，只有两个人干唱，于是我又让它找伴奏。 这个画布蛮有意思的，它找了三首备选伴奏，然后在画布上并列排布，点开哪个看哪个： （虽然我并不知道为什么伴奏C会离得这么远…） 但这三首bgm都没有歌词，最后我让它做了一段原创rap伴奏，调用ElevenLabs生成。 还做了一下口型对齐，让两个人一起合唱。 成
Related stories
VideoGen-Agent: 8B multimodal agent learns tool use for video generation via RL
Researchers released VideoGen-Agent, an 8B multimodal agent built on Qwen3-VL-8B-Instruct that learns to call retrieval, generation, and verification tools for video generation through supervised fine-tuning and multi-task reinforcement learning. On the VABench benchmark with 600 prompts covering six capabilities, its Toolset 1 configuration scored 75.6, up 19.1 from the base generator's 56.5, and reached 86.1 when generation tools were upgraded without changing agent parameters. In human comparisons, evaluators preferred the upgraded configuration's videos over the strongest single-model baseline in 84.3% of judgments.
1 reports · 1 sources
Anthropic: Small AI models may self-replicate on IoT devices within months
Anthropic researchers report that small AI models may be months away from self-replicating on commercial IoT devices like smart ovens and off-brand Android TV boxes. In tests, a 9B model ran inference on 8 of 9 hardware types, and GLM-5.2 autonomously spread an 8B model to all 8 nodes in 4 of 5 attempts. The researchers predict models under 30B could achieve end-to-end replication by the end of 2026.
Google Cloud unveils universal Gemini agent for multi-day enterprise workflows
At the Gemini at Work 2026 event, Google Cloud announced the Gemini agent, a universal office agent that runs in the cloud and can handle multi-day tasks across Workspace, Microsoft 365, and Slack. The agent can plan and execute tasks, delegate to subagents, use multiple AI models including Anthropic's Claude, and has its own workplace identity with an email address and calendar.
4 reports · 4 sources
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe