🔍 Crx搜搜

应用特价

22
Icon Scaler Pro
Microsoft
多媒体设计
多媒体设计 ¥14.00¥7.00
Icon Scaler Pro makes icon resizing fast, simple, and professional. Generate high-quality icons in multiple sizes using ready-made presets, custom dimensions, and multi-resolution ICO export. Fine-tune quality, padding, formats, and output settings with advanced controls — perfect for Windows apps, websites, PWAs, and mobile projects.
0.0
ClipPact Pro – Video Compressor & Converter
Microsoft
多媒体设计
多媒体设计 ¥35.00¥17.50
Compress videos fast. Keep the quality. Save storage. ClipPact Pro is a modern Windows app designed to reduce video file size, optimize videos for sharing, and convert videos with a clean, simple workflow. Whether you want to send a video by email, share it on WhatsApp or Telegram, prepare a video for YouTube, Instagram, Reels, or create a Microsoft Store preview video, ClipPact Pro gives you ready-to-use modes without confusing technical settings. With Simple Mode, just choose a preset and start optimizing. For more control, Advanced Mode lets you adjust codec, resolution, FPS, bitrate, audio settings, output format, metadata removal, and more. All processing is done locally on your device. Your videos are not uploaded to the cloud. ClipPact Pro is built for users who want smaller video files, faster sharing, and professional results without complexity.
0.0
Noise Remover
Microsoft
多媒体设计
多媒体设计 ¥35.00¥17.50
Noise Remover helps you clean and enhance audio completely offline with a simple, privacy-friendly workflow. Remove background noise from voice recordings, interviews, podcasts, lectures, music, and older audio files without uploading anything or requiring an internet connection. Use the built-in A/B Preview to compare original and cleaned audio, choose dedicated Speech or Music modes, or let the new Guided Cleanup Wizard walk you through the entire process step by step. Smart presets and advanced tools such as Hum Removal, Noise Gate, De-click/De-pop, Auto Trim, peak normalization, and channel controls give you more control when needed. You can also process multiple files with Batch Export, generate cleanup quality reports, and export your results in WAV, MP3, FLAC, or M4A.
0.0
QR Code Studio
Microsoft
多媒体设计
多媒体设计 ¥35.00¥17.50
"🌟 QR Code Studio - A Powerful Tool for Crafting Custom QR Codes! 🌟 With QR Code Studio, effortlessly create unique QR codes adorned with beautiful graphic designs, stunning background images, diverse color choices, and customizable size and brightness settings. Boasting a user-friendly interface, this app offers an unparalleled experience in designing and crafting QR codes. Whether for business, advertising, or personal uses, QR Code Studio provides a comprehensive solution to your needs. Download your version now and join thousands of satisfied QR Studio users!"
0.0
画趣
Microsoft
多媒体设计
多媒体设计 ¥15.00¥7.00
用线条勾勒出丰富多彩、充满想象的事和物 功能介绍 ▪ 提供基本的绘图功能,例如铅笔、钢笔、笔刷、粗细、颜色等 ▪ 自定义画板背景色 ▪ 分享您的作品 ▪ 同时打开多个作品进行创作 ▪ 支持鼠标、触控笔、以及触摸 ▪ 简洁的UI,操作简单,无需绘图基础
0.0 0+
ResizeX - Smart Image Resizer
Microsoft
多媒体设计
多媒体设计 ¥14.00¥7.00
ResizeX – Fast & Simple Image Resizer Resize single or multiple images in seconds. Clean modern interface, smart presets, quality control, and batch processing. Perfect for social media, web, and everyday use.
0.0
Voice To Text Converter Pro
Microsoft
多媒体设计
多媒体设计 ¥35.00¥17.50
Voice to Text Converter Pro converts audio and video files into accurate, editable text with support for online recognition and offline Whisper transcription. Use it for meetings, lectures, podcasts, interviews, tutorials, and video content. After transcription, you can edit the text, translate it, create subtitles, and export your work as TXT, DOCX, PDF, SRT, or WebVTT. The new Export Pack saves everything in one organized package: transcript files, subtitle files, PDF/DOCX exports, translation files when available, and a manifest. With improved video handling, recent files, dark/light themes, and a refined Windows interface, the app gives you a focused workflow from media file to usable text.
0.0
ArtRage Vitae
Microsoft
多媒体设计
多媒体设计 ¥564.00¥282.00
ArtRage Vitae is the newest edition of the amazingly realistic natural painting ArtRage workspace. ArtRage Vitae is a digital artist’s studio with a full range of familiar tools that look and work like the real things. It’s a canvas for thick, expressive oils and delicate watercolors, a sketchpad with a full set of pencils, and a sheet of paper with a stack of wax crayons all in one. And now we've added collaboration with a shared ArtRage canvas and chatting with your ArtRage friends. And, you know, a tonne of other fantastic tools.
4.6 13+
AI Tiny Banana
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
用AI Tiny Banana将您的想象力转化为令人惊叹的视觉效果 - 适用于Windows的轻松AI图像生成器。 您是否曾经希望在没有艺术技能或昂贵软件的情况下创建专业质量的图像?AI Tiny Banana使之成为可能。只需描述您所设想的内容,点击生成,然后观看人工智能在几秒钟内将您的文字转化为美丽的艺术作品。 无论您是寻求独特视觉效果的内容创作者、需要快速模型的专业人士、从事项目的学生,还是只是喜欢探索AI创造力的人 - AI Tiny Banana都能提供令人印象深刻的结果,无需学习曲线。 AI TINY BANANA的特别之处: 即时创建:输入您的想法,按下生成,然后接收您的图像。无需复杂设置,无需教程。AI理解自然语言,因此以您觉得自然的方式描述您的愿景。 云端性能:先进的AI模型在云端运行,这意味着强大的服务器处理繁重工作时,您的设备保持响应。在任何Windows PC上都能流畅运行。 灵活的输出选项:将您的创作保存为高质量PNG文件,或直接复制到剪贴板以便在其他应用程序中立即使用。非常适合演示文稿、社交媒体、文档或个人收藏。 实时反馈:通过视觉指示器观察生成进度。如果您想尝试不同的提示,可随时取消。直观的界面让您随时了解每一步。 会话管理:每个创意会话都保持上下文,您可以随时重置以全新想法重新开始。 完美用途: - 社交媒体内容和缩略图 - 博客和文章插图 - 创意头脑风暴和概念艺术 - 教育材料和演示文稿 - 个人艺术项目和实验 - 快速模型和视觉原型 AI Tiny Banana将尖端AI技术与简洁现代的Windows界面相结合。应用内无需管理订阅,创作上无水印,只有纯粹的创作自由触手可及。 今天就开始创作。您的想象力是唯一的限制。 立即下载AI Tiny Banana,发现AI图像生成可以多么简单。
0.0
AI FFmpeg
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
用AI驱动的简洁方式转换您的媒体文件。AI FFmpeg消除了FFmpeg命令行语法的复杂性,使专业级的视频和音频处理变得触手可得。 只需用简洁的英文描述您的需求 - "转换为MP3"、"缩放到720p"或"提取音频" - AI FFmpeg会立即生成完美的FFmpeg命令,完全符合您的文件需求。无需技术知识,无需查阅手册,只需自然语言指令就能交付专业成果。 核心功能: 自然语言命令:用日常语言描述您的任务,让AI生成所需的精确FFmpeg命令。我们的智能系统会分析您的媒体文件属性并自动创建优化的命令。 智能媒体分析:内置探针技术检查您的文件并提供详细信息,包括编码器、分辨率、比特率、时长和元数据。AI利用这些数据创建完全优化的转换命令。 一键预设:快速访问常见任务,如音频提取、视频压缩、格式转换、分辨率更改和速度调整。完美适合需要快速结果的用户。 实时进度跟踪:通过准确的百分比跟踪和清晰的状态更新监看您的转换进度。 对话式工作流:保持对话历史以根据之前的尝试优化命令。如果有问题,只需请求调整,AI会从反馈中学习以生成改进的命令。 错误恢复:转换失败时,AI分析错误日志并自动建议纠正后的命令来修复问题。 命令导出:将生成的命令保存为文本文件、批处理脚本或shell脚本,用于将来使用或自动化工作流。 支持的操作: • 视频格式转换(MP4、MKV、AVI、MOV等) • 音频提取和转换(MP3、AAC、WAV、FLAC) • 分辨率缩放(720p、1080p、4K、自定义尺寸) • 视频压缩与质量保留 • 帧率调整和编码器选择 • 音频轨道管理和字幕处理 • 视频速度修改 • 缩略图和帧提取 • 比特率优化和元数据编辑 完美适用于: • 为不同平台转换视频的内容创作者 • 提取和转换音频文件的播客制作人 • 为编辑工作流准备媒体的视频编辑者 • 自动化媒体处理任务的开发者 • 学习视频/音频处理技术的学生 • 任何需要可靠媒体转换且无需技术专长的人 为什么选择AI FFmpeg: 节省时间:数秒内生成复杂的FFmpeg命令,无需花费数小时研究文档。AI验证确保命令在执行前语法正确。 隐私优先:所有处理都在您的设备本地进行 - 您的文件永远不会离开您的计算机。捆绑的FFmpeg可执行文件确保即时功能,零设置需求。 学习工具:查看生成的命令以理解FFmpeg语法并学习高级技术,同时AI处理复杂性。 将繁琐的命令行工作转化为简单的对话。立即下载AI FFmpeg,体验媒体转换的未来。
0.0
ImagineIt
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
使用ImagineIt——Windows强大的AI图像生成器,瞬间将文字转化为惊人的图像。无论您是创意专业人士、内容创作者,还是刚开始探索AI艺术世界,ImagineIt都能让您轻松将想象变为现实。 为什么选择ImagineIt? 创建独特、高质量的图像从未如此简单。只需输入您想看到的内容,高级AI技术就会在几秒内将您的文字转化为精美艺术作品。无需复杂设置、无需订阅费用、无需云依赖——一切都在本地设备上运行,确保最大隐私和速度。 采用Stable Diffusion技术支持 ImagineIt利用尖端的Stable Diffusion模型在Windows PC上生成专业级图像。应用支持GPU加速,可极速生成图像,完美适合快速原型制作、创意探索和专业工作流程。 完美适用于: • 内容创作者:为社交媒体、博客和营销素材生成独特视觉内容 • 设计师与艺术家:探索创意概念、制作灵感板、开发创意想法 • 教育工作者与学生:将抽象概念可视化、增强演示文稿 • 爱好者:体验AI艺术、释放创意潜能 • 专业人士:为项目创建自定义图像,无需受库存图片限制 主要优势: 完全隐私——所有图像生成都在本地设备上进行。您的提示词和创作永不离开计算机,确保绝对隐私和数据安全。 无额外费用——与云端服务不同,无月费或使用限制。下载应用后可生成无限图像。 快速生成——GPU加速支持让您在几秒内获得图像。优化的Stable Diffusion.cpp引擎确保最高性能。 可定制输出——通过调整图像尺寸、采样方法、CFG值、推理步数和负面提示词等参数,精确控制生成结果。 LoRA支持——使用LoRA(低秩适应)模型扩展功能,实现特定艺术风格、角色一致性或专业图像类型。 易于使用——简洁直观的界面,实时进度追踪。输入提示词并点击生成,就是这么简单。 高级功能: • 支持多个Stable Diffusion模型(SD 1.5、SD 2.1、SDXL、SD3) • GPU和CPU执行模式 • 可调图像分辨率(宽度/高度) • CFG值控制以提高提示词遵循度 • 自定义采样方法 • 负面提示词支持以排除不需要的元素 • CPU VAE选项用于内存优化 • 内置超分辨率处理以生成高分辨率输出 • 会话历史记录便于查看和重访您的创作 谁应该使用ImagineIt? ImagineIt适合任何想要无复杂性地探索AI生成艺术的用户。从初学者的AI创意第一步到需要可靠、私密图像生成工具的专业人士,ImagineIt都能提供简化的Windows应用中的Stable Diffusion强大功能。 今天就用ImagineIt开始创作惊人的AI生成图像——让您的想象力与智能技术相遇。
0.0
Media Info Inspector - for Video, Audio and Pictures
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
Media Info Inspector: Your Multimedia Deep-Dive Tool Unlock the full potential of your multimedia files with Media Info Inspector, the all-encompassing analysis tool tailored for videos, audios, and pictures. Powered by the reliable ffprobe.exe, this app is your one-stop solution for dissecting and understanding the intricate details of your media files. Effortless Media Analysis Simply drag and drop any media file into Media Info Inspector and witness a detailed breakdown of its properties. Save the insights as a JSON profile or input a URL to examine online media files directly within the app. Explore the Raw Data For the data enthusiasts, Media Info Inspector grants direct access to the raw JSON information, providing a transparent look into your media files’ data. Key Features: - Drag & Drop Analysis: Instantly analyze your media files with a simple action. - Versatile Media Compatibility: Extensive support for various media file formats. - Saveable Media Profiles: Export your media analysis as a JSON document. - Direct URL Input: Analyze media files from the web with just a URL. - Raw JSON Access: View and study the complete JSON data of your media files. Whether you’re a seasoned photographer, an audiophile, or a video aficionado, Media Info Inspector is the indispensable tool for gaining comprehensive insights into your media files. Download Media Info Inspector now and transform the way you interact with your multimedia content!
0.0
Faster AI Speech Studio
Microsoft
多媒体设计
多媒体设计 ¥28.00¥18.76
使用强大的离线语音生成功能将文本转换为逼真的语音。由 Piper 和 Parler AI 引擎提供的专业 TTS 工作室。无需订阅或字符限制,即可创建有声书、配音和叙述。 **Faster AI Speech Studio** 是一个完整的离线文本转语音平台,能够将您的文字转变为自然、逼真的人类声音。与按字符收费且需要网络的基于云的 TTS 服务不同,我们的应用在您的桌面上提供无限制的专业级语音生成。 无需月费或字符配额,即可创建专业配音、有声书和旁白。无论您是 YouTuber、教育工作者、作者还是开发者,都能在完全隐私和零持续费用的情况下生成工作室级别的语音。 **高级语音合成** • 双引擎驱动:Piper TTS 和 Parler TTS 神经模型 • 50+ 种语言的数百种自然语音 • 多扬声器支持,各具特色 • 调整语速、情感和语调 • GPU 和 CPU 加速 **基于项目的工作流程** • 创建无限的 TTS 项目,并自动备份 • 用于组织语音段的可视化时间线编辑器 • 独立编辑各个语音段 • 拖放时间线排列 **语音克隆和自定义** • 从音频样本克隆语音 • 访问数百个预训练的扬声器模型 • 在一个项目中混合不同的语音 • 微调语音参数 **智能文本处理** • AI 驱动的文本分解,实现自然表述 • 多种分割方法:换行、标点符号、AI 辅助、自定义 • JSON 批处理和自动化 **时间线和音频管理** • 实时预览和播放 • 集成媒体播放器,具有时长跟踪 • 导出高质量 WAV 文件 • 复制、重新排序和编辑语音段 **50+ 种语言** 英语(美国、英国、澳大利亚、印度)、西班牙语、法语、德语、意大利语、葡萄牙语、中文、日语、韩语、阿拉伯语、俄语、印地语等,具有本地发音。 **100% 离线和隐私** • 所有处理都在本地进行 • 您的文本和音频不会离开您的计算机 • 无使用限制或订阅 • 完全隐私 **完美用途:** ✓ YouTube 视频、播客、有声书 ✓ 电子学习材料 ✓ 游戏角色语音 ✓ 营销视频 ✓ 无障碍工具 ✓ 视频配音 **使用场景:** YouTube 旁白、有声书制作、电子学习课程、播客介绍、游戏对话、无障碍功能、营销视频、自动化公告、多语言本地化。 **技术卓越:** 基于 Piper TTS 神经声码器和 Parler TTS 集成。内存占用少、WinUI 3 界面、便携式项目格式。 与昂贵的云 TTS 服务不同,Faster AI Speech Studio 为您提供无限的专业语音合成,无需持续费用。生成数小时的音频,无需成本、连接或配额限制。 无需订阅。无需网络。无限可能。
0.0
AI Smart Background Remove
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
AI Smart Background Remove 是一款强大的隐私优先背景移除工具,完全在您的设备上运行。凭借先进的人工智能技术,它能智能检测照片中的主体并精确移除背景——无需将任何图片上传到云端。 无论您需要干净的产品照片、专业的人像照片还是创意合成图,AI Smart Background Remove 都能在几秒钟内提供影棚级质量的结果。只需拖放您的图片,让 AI 完成剩下的工作。 核心亮点 • 100% 离线处理——您的照片永远不会离开您的设备。无云端上传、无数据收集、无隐私顾虑。所有处理都在您的电脑上本地完成。 • 批量处理——一次性移除数十甚至数百张图片的背景。非常适合处理大量照片的电商卖家、摄影师和内容创作者。 • 拖放操作的简便性——无需复杂的菜单或设置。只需将图片拖入应用程序,即可获得即时结果。 • AI 驱动的精准度——先进的神经网络技术准确检测人物、动物、物体和产品,生成边缘平滑的干净抠图。 • 快速性能——经过优化以充分利用您的硬件,即使在处理大批量图片时也能快速移除背景。 适用场景 • 电商和网店产品摄影 • 社交媒体内容创作 • 专业人像和肖像照片 • 平面设计和营销素材 • 个人照片编辑和创意项目 AI Smart Background Remove 将专业级 AI 与拖放操作的简便性相结合。无需订阅、不依赖云端、没有学习曲线——直接在您的 Windows 电脑上享受快速、精确且私密的背景移除。
0.0
AI Media Toolkit
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
使用 AI Media Toolkit 轻松转换您的媒体文件 - 这是一款能够理解简单中文的智能视频、音频和图像处理应用程序。 不再需要与复杂的视频编辑软件搏斗或记忆晦涩的命令行语法。AI Media Toolkit 让您用日常语言描述您想要的内容,我们的 AI 助手会立即生成完美的 FFmpeg 命令。无论您是内容创作者、开发人员还是普通用户,您都能在几秒钟内完成以前需要数小时学习才能完成的工作。 智能媒体处理 只需告诉 AI 您需要什么:"将此转换为 MP4"、"缩小视频"、"提取音轨"或"将播放速度加快 2 倍"。AI 理解您的意图,并创建针对您特定文件优化的命令。无需技术专业知识。 全面的格式支持 几乎可以处理任何媒体格式。处理视频(MP4、AVI、MKV、MOV、WebM)、音频文件(MP3、WAV、FLAC、AAC、OGG)和图像(JPG、PNG、GIF、BMP、WebP)。在格式之间转换、调整质量设置,轻松处理批量操作。 强大的快速预设 一键访问最常见任务的解决方案: - 视频:转换为 MP4、调整为 720p、提取音频、压缩文件大小、裁剪片段、调整播放速度 - 音频:转换为 MP3/WAV、标准化音量级别、增强音频、裁剪音轨 - 图像:转换格式、调整尺寸、网页压缩、创建视频幻灯片、旋转和裁剪 详细的媒体分析 在处理之前,获取有关文件的完整信息。查看分辨率、编解码器信息、时长、比特率、帧率等。对压缩和转换设置做出明智的决策。 对话式界面 与 AI 助手自然聊天。提出后续问题、完善您的请求,并在此过程中了解媒体处理。对话历史记录会跟踪您的会话,使复杂的多步骤工作流程变得简单。 跨平台可靠性 基于专业级 FFmpeg 技术构建,AI Media Toolkit 在 Windows 和 macOS 上都能提供一致的结果。您的媒体处理工作流程在所有设备上都以相同的方式运行。 无论您是为社交媒体准备视频、转换播客音频、为网站优化图像还是探索创意可能性,AI Media Toolkit 都将专业的媒体处理能力触手可及 - 无需学习曲线。 立即下载 AI Media Toolkit,体验直观媒体转换的未来。
0.0
Audio Enhancer Pro
Microsoft
多媒体设计
多媒体设计 ¥49.00¥28.00
Audio Enhancer Pro helps you turn ordinary audio into a clearer, richer, and more polished listening experience. Whether you want to improve voice recordings, podcasts, meetings, videos, music, lessons, or older audio files, this app gives you simple one-click presets and advanced controls to enhance your sound with confidence. Choose from ready-to-use modes such as Voice Clarity, Podcast Enhancer, Music Booster, Noise Reduction, Bass Boost, Speech Enhancer, Studio Clean, Old Recording Restore, Meeting Audio Improve, Video Voice Polish, and more. You can reduce background noise, improve clarity, adjust bass and treble, normalize volume, control peaks with a limiter, use compression, reduce harsh sibilance, and fine-tune the final output when you need more precision. The app also supports batch enhancement, so you can process multiple audio files at once using the same enhancement settings. Select your files, choose an output folder, and let Audio Enhancer Pro create enhanced versions without overwriting your existing files. Preview your enhanced audio before saving, export in popular formats, and keep track of your processed files through the built-in history panel. No complicated setup. No confusing workflow. Just open your audio, choose a mode, preview the result, and save a cleaner, stronger, better-sounding file.
0.0
ATM悟文韬声字幕组Pro
Microsoft
多媒体设计
多媒体设计 ¥199.00¥99.50
小米MiMo AI驱动 · 一键无限长文稿转人声与高级校准SRT字幕的一键完成视频字幕组的终极APP。默认内置开源软件FFmpeg LGPL,用户可使用本地配置版。 用剪映等工具生成的字幕,无法做到100%逐字对应原稿,中英混排、数学公式、物理符号、科技参数等专业内容错误频发,每次都要人工逐句校对,耗时耗力。而且这些工具不提供字幕断句的自定义能力,经常丢失文稿中的字符,想要使用高级功能还需要SVIP年费订阅。克隆人声?必须本人当场对着麦克风朗读。 ATM悟文韬声字幕组Pro,一次性买断,永久使用,零订阅费。 核心优势: • 逐字精准念稿 — 100%逐字朗读文稿,不增删、不修改,自动保留复杂段落格式 • 文字描述创造人声 — 独特的声音设计功能,只需用文字描述你想要的音色特征(如"赛博朋克女黑客"),AI即可生成对应人声,无需任何音频样本,创意无限 • 试听并锁定 — 声音设计生成的音色可先试听,满意后一键锁定,确保后续所有音频音色完全一致 • 15秒极速克隆人声 — 仅需一段不到15秒的WAV音频,即可克隆生成无限人声,无需本人当场朗读,不限制朗读内容 • 内置官方人声 — 提供Xiaomi MiMo官方多种音色可选,开箱即用 • 无限文本长度 — 无字数限制,支持超长文稿一次性处理 • 批量文件导入 — 直接批量导入TXT、MD文件,高效省时 • 精准SRT字幕 — 内容100%跟原文稿一样,不改字删字。时间轴使用ATM AI自研韬定律高级SRT算法生成,质量接近专业人员手打。人工校准字幕时间远远小于剪映6.0。 • 本地处理 — 音视频字幕处理在本地完成,保护隐私 • 一次性买断 — 无年费、无订阅、无内购,一次付费终身使用 • 众多设置高度自定义,默认配置已经生产力足够好。 适用人群: 自媒体创作者、短视频UP主、有声书制作者、播客主播、教育工作者、企业培训、多语言内容创作者、任何需要将文字转为人声和字幕的用户。 ATM AI官方使用此APP构建的长视频: https://www.bilibili.com/video/BV1QpEm6qEem/ https://youtu.be/I21p-wmNG7g Powered by Xiaomi MiMo AI · One-click unlimited-length text/MD to human voice/speech and precision-calibrated SRT subtitles — the ultimate one-click app for video subtitle teams. Built-in open-source FFmpeg (LGPL) by default; local custom version supported. Subtitle tools like CapCut/JianYing generate subtitles that fail to match your script character-by-character. Mixed Chinese-English text, math formulas, physics symbols, and technical parameters are riddled with errors, requiring manual line-by-line proofreading. These tools offer no custom subtitle segmentation and often drop characters from your script. Want advanced features? You need an SVIP annual subscription. Voice cloning? You must read aloud in person, in real time. ATM WuText TauSpeech Subtitling Crew Pro — one-time purchase, zero subscription fees, yours forever. Key Advantages: • Verbatim Script Reading — 100% character-accurate narration, no additions, no deletions, no modifications. Complex paragraph formatting is automatically preserved. • Text-to-Voice Design — A unique voice design feature: simply describe the voice you want in text (e.g. "cyberpunk female hacker"), and AI generates a matching voice — no audio sample needed, unlimited creative possibilities. • Preview & Lock — Preview the AI-designed voice before committing. Once satisfied, lock it with one click to ensure consistent voice across all generated audio. • 15-Second Voice Cloning — Clone any voice with just a WAV audio clip under 15 seconds. No need to read aloud in person. No restrictions on content. • Built-in Official Voices — Multiple Xiaomi MiMo official voice options ready to use out of the box. • Unlimited Text Length — No character limit. Process ultra-long scripts in one go. • Batch File Import — Directly import TXT and MD files in batch for maximum efficiency. • Precision SRT Subtitles — 100% faithful to the original script; no word is changed or deleted. Timelines are generated using ATM AI’s proprietary Tau (τ) Scaling Law advanced SRT algorithm, delivering quality approaching professional manual transcription. Manual subtitle calibration time is far less than with CapCut 6.0. • Local Processing — Audio, video, and subtitle processing is performed locally on your device, protecting your privacy. • One-Time Purchase — No annual fees, no subscriptions, no in-app purchases. Pay once, use forever. • Highly customizable with extensive settings, yet the default configuration is already production-ready. Ideal For: Content creators, video streamers, audiobook producers, podcasters, educators, corporate trainers, multilingual content creators, and anyone who needs to convert text into human voice and subtitles. ATM AI Official Long Videos Built with This App: https://youtu.be/I21p-wmNG7g https://www.bilibili.com/video/BV1QpEm6qEem/
0.0
Onwords
Microsoft
多媒体设计
多媒体设计 ¥169.00¥135.20
STOP READING AT A MACHINE'S PACE Anyone who has recorded to a teleprompter knows the feeling. The text is moving, you're not quite with it, and every take becomes a negotiation between how you want to say the line and how fast the words are sliding past. Speed it up and you gabble. Slow it down and you drift. The performance ends up serving the equipment. Onwords removes that negotiation. It listens through your microphone, works out where you are in your script, and scrolls the text to keep your current line centred on screen. You speak at whatever pace suits the material, and the script keeps up with you. No clicker. No operator sitting off-camera. No guessing. FORGIVING BY DESIGN Real delivery is never a clean read-through. You'll stumble, repeat a phrase, drop in an unscripted aside, or jump a paragraph because the previous take already covered it. Onwords is built for that. It needs only a few recognisable words to hold its place, so a fluffed line or a filler word won't throw it. When it isn't confident about what it heard, it holds position rather than guessing and leaping somewhere wrong. And when you do move somewhere unexpected, it searches the whole script and picks you back up within a sentence or two. YOUR SCRIPT NEVER LEAVES YOUR COMPUTER Speech recognition happens on your own machine, using the engine built into Windows. There is no cloud service, no API key, no account to create, and no internet connection required at any point. No audio is recorded or stored. Nothing is uploaded. That matters when you're working on something under embargo, under NDA, or simply not finished yet. TWO PRESENTERS, ONE SCRIPT Co-hosted shows, interviews and double-act pieces all break a normal teleprompter the same way: one undifferentiated block of text, with no warning that your line is next. Onwords lets you assign lines to either presenter and tints them on screen - pale yellow and pale blue - so a handover is something you see approaching rather than something you discover. Tracking carries straight through the changeover, because it follows whoever is talking. Both presenters share one microphone. Assignments are stored in the script itself, so they survive editing, they save with your script, and a script that already marks up its speakers works as soon as you paste it in. BUILT FOR HOW PEOPLE ACTUALLY FILM Mirror the text horizontally for beam-splitter teleprompter hardware. Scale it up for distance from the screen, or down to fit more on. Run it full screen on a second monitor so the prompter display stays clean while you keep the controls on your laptop. A live transcript shows you exactly what the app is hearing, so nothing about the tracking is mysterious. The arrow keys nudge your position by hand at any moment, and the mouse wheel scrolls freely whenever you want to look ahead. And if you'd rather not use your voice at all, a classic constant-speed scroll with an adjustable rate is still there. A REAL WINDOWS APP Onwords is built with WinUI, the current native Windows interface framework. It starts quickly, sits at almost no CPU while you read, and doesn't drag a browser engine along with it. Native builds for both Intel and ARM processors. Your script is saved automatically and restored next time you open the app, so there's no re-pasting between takes or between days. WHO IT'S FOR Video creators recording to camera. Corporate and marketing teams producing internal and customer-facing video. Speakers and presenters delivering keynotes. Educators and course creators recording lessons. Livestreamers and webinar hosts who can't stop to find their place. Podcasters working from a scripted structure. And anyone recording alone, with nobody available to run the prompter for them. A NOTE ON ACCURACY Onwords uses the speech recogniser built into Windows, which will mishear unusual names and technical jargon. Onwords is designed to track well in spite of that, rather than to transcribe you accurately. It follows your position in a script you have already written — it is not a dictation tool.
0.0
Picock
Microsoft
多媒体设计
多媒体设计 ¥104.00¥71.00
Turn an idea into an image—and any image into a reusable prompt. PICOCK is a modern AI image studio for Windows, built around a clear and efficient creative workflow. Generate original visuals from text, explore curated styles, compare multiple results, and keep your work organized in one streamlined desktop workspace. CREATE FROM WORDS Describe the subject, style, mood, lighting, and composition you want. Refine your prompt with AI assistance, add useful phrases, randomize ideas, choose landscape, portrait, or square format, and generate multiple variations without interrupting your workflow. TURN ANY IMAGE INTO A PROMPT Import an image from your computer—even if it was created outside PICOCK. Image to Prompt analyzes its visual qualities and produces an editable description that you can copy, improve, or send directly to the generator. Use it to study composition, understand a visual style, recreate a creative direction, or build a stronger starting prompt from an existing image. EXPLORE CREATIVE STYLES Browse a collection of curated visual styles, including illustration, watercolor, anime, pixel art, cinematic looks, and more. Preview different creative directions and quickly find a style that matches your idea. REVIEW, IMPROVE, AND REUSE Compare generated results, return to earlier prompts, inspect useful image details and seed information, and upscale the images you want to keep. Save, copy, and export finished creations directly from the app. MAKE YOUR ART PART OF WINDOWS Turn a favorite creation into your Windows desktop wallpaper directly from PICOCK. TRY BEFORE YOU BUY Explore PICOCK with the free trial. When you are ready, unlock continued use with a single purchase. There is no recurring subscription. Whether you are creating desktop wallpapers, concept art, character ideas, illustrations, social visuals, or visual inspiration, PICOCK gives you a practical path from idea to finished image—and from an existing image back to a reusable prompt.
0.0
Fast Video Stabilizer
Microsoft
多媒体设计
多媒体设计 ¥35.00¥23.45
Fast Video Stabilizer 将抖动的手持视频变成平滑、专业级的画面 —— 完全在你的 Windows 电脑上本地处理,无需云端、无需等待。 为什么 手持视频有个通病:每一步、每一次颠簸、每一丝手的晃动都会变成画面抖动。专业相机内置光学或电子防抖,而你的手机和摄像头没有。 Fast Video Stabilizer 用一个纯 C 编写的双通道引擎解决它。首先逐帧扫描视频,精确绘制相机运动轨迹 —— 每一帧之间移动和旋转了多少。然后平滑这条轨迹并重新渲染每一帧,让成片看起来就像用了云台拍摄。 核心能力 ★ 双通道稳定引擎 —— 先检测相机运动,再修正,实现最大平滑度 ★ 抖动分析 —— 渲染前告诉你的素材有多抖(低 / 中 / 高),并建议合适的强度 ★ 0 到 10 可调强度 —— 从轻微平滑到强力修正 ★ 两种修正模式 —— Smooth 适合日常手持视频,Optical 适合剧烈抖动素材 ★ 智能裁剪控制 —— 保留完整画面或裁掉防抖边距 ★ 音画同步 —— 稳定后的输出中音轨保持完美对齐 ★ 可选锐化 —— 抵消防抖带来的轻微柔化 ★ 实时进度 —— 查看当前通道、百分比和时间估算 ★ 随时取消 —— 停止长时间稳定处理而不损坏文件 ★ 完全本地 —— 你的视频永远不离开这台电脑 适合场景 • 手机旅行 Vlog 和城市漫步 • 没有云台拍摄的运动和动作镜头 • 无人机素材和手持云台补救 • 需要清理的安防或行车记录仪片段 • 任何没有使用三脚架的拍摄 现代 Windows 体验 Fast Video Stabilizer 基于 Windows 11 的现代 WinUI 3 框架构建 —— 快速、干净的界面,原生深色模式,清晰字体,零冗余。打开视频,查看分析,点击稳定。 你的视频。你的电脑。你的平滑画面。
0.0