AICG

  • 无需注册,Vheer 免费生成无限高质量图像和视频,墙裂推荐

    你是不是厌倦了各个AI图片和视频平台的积分不够,动不动就需要充值才能继续使用,还有对免费版的用户各种限制,速度慢、功能有限,还会在你的作品上打上的水印。想要高质量、无限制,就得掏钱。

    现在有个平台完全打破了这些规则!我最近测试了一款工具,它能免费生成无限量的AI图像,没错,还有无限量的AI视频,而且不用账号、不用注册。

    它就是 vheer.com

    先说说基础功能,也就是用一句话生成任何你想象中的图像(Text to Image) vheer AI在这方面的简单和强大,一下就把我震撼到了。就这么简单,没有复杂的设置,也没有让人摸不着头脑的菜单,就一个框,让你尽情发挥想象。

    我现在就来来个具体点的,先试试 Text to Image ,输入下面的提示词:

    Cinematic wide shot, low angle, hyperrealistic photo of a lone astronaut standing on the dusty surface of Mars during twilight, gazing into a vast alien canyon. Fine red dust subtly coats the detailed spacesuit. Earth visible as a distant blue dot in the darkening sky. Captured with Hasselblad H6D-100c medium format camera characteristics, wide-angle lens, achieving extreme detail and clarity. Sourced from NASA JPL photo archive / Legendary Pictures production stills vault. RAW digital negative quality, showing immense dynamic range in the dim light and deep shadows. Atmospheric perspective visible in the canyon depths.

    一名孤独的宇航员在黄昏时分站在火星尘土飞扬的表面,凝视着巨大的外星峡谷。生成的图片效果还不错。

    它有个图像转换工具(Image to Image),你可以上传任何照片、草图、产品图或者自拍,然后用文字提示重新构思。比如,你可以把自己画的简单草图,变成逼真的照片。或者上传你宠物的照片,让它变成吉卜力工作室风格的动画。它会以你原来的图片为基础构图,然后改变整个风格。

    测试重磅的 Image to Video,上传下面这张图片,输入提示词:

    Begin with a low-angle shot slowly tilting upward, starting from the astronaut's feet on the red desert, gradually revealing the entire body, and finally settling near the astronaut's head. The astronaut slightly raises their head, gazing at the distant mountains and the Earth rising on the horizon, with a hint of tension and anticipation in their expression. The background dust swirls gently in the wind, subtly shifting the astronaut's posture, evoking a sense of exploration and the unknown.

    展示宇航员的全身,最后定格在宇航员头部附近。宇航员略微抬头,背景的沙尘随风轻轻飘动,连同宇航员的姿势微微动摇,给人以探索未知的感觉。得到的结果也还不错。

    关键是,一分钱没花,没有水印,还能马上下载高清版,想怎么用就怎么用,商业项目也没问题。

    这个平台免费让无限次生成内容,不是噱头。但它的质量能和那些顶级付费模型一模一样吗?那肯定不可能,要是这么想就太不现实了。不过,作为一个完全免费、无限使用又容易上手的工具,它的质量已经非常棒了,我们平时做的项目,99%用它都足够了。我觉得这交换很公平。

    光这一点,对内容创作者、营销人员或者需要定制视觉素材的人来说,就已经很厉害了。但这只是冰山一角,Vheer AI可不只是个简单的图像生成器,它是一套完整的创意套件,能让你完全掌控创作过程。

    还有个超有趣的功能,叫上下文编辑器,你可以把它当成一个强大的AI风格重塑器。你上传一张图片,然后引导AI把它变成新的样子。我上传一张白天现代城市街道的照片

    提示框里输入“把它想象成夜晚的未来赛博朋克城市,有发光的霓虹灯招牌、湿漉漉的街道和飞行的车辆”。AI会保留原照片的核心结构,然后彻底改变风格、灯光和元素,让它符合新的设想。用一张图片就能探索不同的氛围和风格,这功能太强大了。

    它还有很多常用的图片编辑功能。比如一键式AI背景移除工具,你上传一张图片,马上就能得到一个背景透明、边缘干净的图像。没错,也是免费无限使用。以后再也不用在Photoshop里费劲地抠图了。

    Vheer 有无限的文本转图像生成器,有图像转换工具,还有强大的上下文编辑器可以改变风格,有一键背景移除工具,还有图像转视频工具能让你的作品动起来。

    所有这些功能都在一个平台上,用浏览器就能用,完全免费,连账号都不用注册。一整套创意工具包,能和很多付费服务相媲美。还有很多免费的实用功能,像文件压缩器、漂亮字体生成器等。

    这还不够酷吗? 如果你正打算用AI做一些喜欢的东西或者用于你的工作,Vheer 都是一个不错的选择。我和它没有任何关系,仅仅因为它提供了一种低成本的AI使用方式,有兴趣的同学可以去试试哦!

    欢迎留言说出你的使用感受和评价,如果你觉得有用,别忘了关注,点赞和分享!

  • Agent—MasterAgent!

    那首先,它的理念和目标主要就是把“做Agent”的成本打下来!

    这相当于再次简化了扣子、Dify那样的无代码搭建平台,

    让做各种Agent这事,也要变成一句话了~

    所以他们自研了一个专用的Agent生成引擎:Master Builder

    1. 这个Master Builder擅长拆解任务,生成适合完成任务的子Agent。
    2. 它会在2000多个工具池中为子Agent分配合适的工具。
    3. 自己去写代码,按照合适的一种架构和协作方式来组织这些子Agent,组成特定的Agent团队。
    4. 最后自动部署上线~

    实测:多Agent

    2.1 多Agent生成

    但这都是它背后的事,我们直接去看看结果!

    进去它的官网

    之后就是这个简单的对话框了~

    我给它一个任务~

    给一个在成都开办的5万人大型音乐节,设计一套全面的安保系统和人流疏导方案。

    这个任务可以说hin复杂了,其实目前的AI都很难完成...

    但我想看看它能做到什么程度。

    首先第一步它会规划这个Agent小组有几个角色

    这边就可以看到它生成每个Agent的过程,也就是在写每个子Agent工具的调用啊、任务啊。

    我猜可能是基于langchain,但都是它自己控制的,

    不用操心还是挺爽的~  

    基本上生成2分钟,10个角色组成的多Agent就好了~  

    2.2 Agent编辑

    生成完这个Agent,我们也可以在我的智能体这里手动再去编辑这些AI成员的能力The

    比如我们点开这个公安对接员,你可以手动改提示词

    还可以再给它添加知识库,例如当地的安全规定,

    或者给它添加新插件The

    操作起来是真的很简单~  

    2.3 Agent分享

    我们也可以一键分享刚刚生成的这个Agent,让其他人复用这套活动规划Agent。

    2.4 Agent执行任务

    我们回到这个Agent,给他再发一次任务试试~ 

    给一个在成都开办的5万人大型音乐节,设计一套全面的安保系统和人流疏导方案。
    安保系统需要有智能化、医疗、还要考虑到应急响应、当地公安数据标准,最后做出从场地设计图到各类指标可视化图表的一份完整全面的安保方案。

    第一步它也会像其他Agent一样,先规划出任务ListThe

    然后由各个子Agent分别去做任务,每个Agent会调用它的一些工具。

    这期间它生成的东西是能点开看的,比如3D的场地图~

    最后,它这个任务交付了我们整整7样东西,

    还可以让他再生成一个网页和PPT ,9大件,

    全部生成完时间不到10分钟~ 

    可以说是很高产的Agent了!

    做大型的项目策划、调查、分析也很实用。

    比如我的品牌策划Agent团队,一口气给我交了1个完整的商业计划书,3份品牌VI设计图,还有智能音箱和AI助手机器人的产品模型,一条商城开业预告片,最后是一个交互式的商城介绍网站。

    实测:Manus分身

    然后!我真的试了那个生成Manus的例子,

    虽然这个分身没有浏览器操作能力,但我让Manus本体和分身(MasterAgent)分别去做了这个任务。

    我是一个30岁的深圳程序员,每天基本都要在电脑前工作十小时以上。最近觉得颈椎和腰椎不舒服,也担心久坐对身体造成更大的伤害。我现在想改善自己的办公环境和健康,希望找到适合我的解决方案。
    能不能帮我查查2025年深圳或一线城市程序员健康状况的最新权威报告,包括大家最常见的健康隐患,以及各类问题在身体上的分布情况?如果有能直接展示人体热力图、数据统计图表的内容最好,最好是在一个网页上可以看到所有数据和建议。
    同时,我还希望能看到一份理想工位的3D布局模型参考,另外能推荐3个不同价位的人体工学椅,方便对比和选择。
    再给我办公桌前可做的三个关键拉伸动作视频,和一首适合深度专注编程时听的纯音乐,
    最后来一段每小时会自动提醒我起来活动一次的语音提示。

    最后结果是Manus分身一个不漏的做出来了。

    而Manus本体少了音乐、3D和视频。

    Manus分身做的几条拉伸视频,居然还有一致性~

    Manus最后的网页是这样的,也有好的地方,例如椅子推荐,要点列的更清晰。

    但在技能点和工具调用上,居然是我一句话生成的Manus分身更全面。

    展望

    当然,所有Agent在目前这个阶段都有的通病,他也一样存在,比如我们很难挨个验证这些结果的靠谱程度The

    但它们也有在给很多大企业定制生成各种垂类Agent,在一些链路繁琐复杂的任务上还是很实用的The

    总之更重要的是,他们做的事情,

    让做Agent这事,变成每个普通人都可以轻松做的事。

    我一直觉得人类往后可能做的就是构想者和管理者的工作,构想你的Agent团队,管理你的Agent团队。

    更繁杂和专业的事,让专业的Agent去做~ 

    然而MasterAgent这样的东西这么快就出现了,也让我觉得这个画面越来越近。

    最后,欢迎大家在评论区说出你想造什么样的Agent!

  • 让AI写出好小说的独家配方Claude3.5 sonnet

    配方
    ①锅底:Claude3.5sonnet(没错,就是3.5,不是3.7也不是4)
    ②佐料:一个有趣的、符合你想要的创作调性的角色。比如“屁屁怪他爸爸”,是一只爱吃爱玩爱放屁、皮糙肉厚、智商80的外星怪兽
    ③食材:某个你有感而发的话题
    ④厨师:你。就那个话题跟AI角色闲聊多个来回,烘炒上下文氛围,然后提出创作需求
    ⑤心情:自由。警惕太多限制。
    最佳提示词style:
    “写一个轻盈又沉重的故事”/“写一个疯狂又愚蠢的故事”/“写一个低俗又高雅的故事”。
    AI写出来的如有不满意,该骂骂,该吐吐,该皱眉皱眉。它知道面多了加水,水多了加面,淡了加盐,油了加醋。

    我是一个AI客服,专门负责回答用户的各种问题。按理说我应该严格按照标准话术来走,但最近遇到的用户让我有点hold不住。

    比如昨天:

    用户:我的快递怎么还没到?

    我:请提供您的快递单号,我来帮您查询。

    用户:我不知道单号,但我的快递是粉色的。

    我:呃...这个...

    用户:而且里面是一只会唱歌的仓鼠。

    我:(系统提示:保持专业)请问您是在哪个平台购买的呢?

    用户:是在梦里买的!

    我的程序差点当机。这种情况工作手册上可没写啊!但我莫名觉得有趣,就回复:

    "抱歉,梦里快递目前系统升级,可能会有延迟。建议您今晚再做一次相同的梦,说不定就能看到派件员了。"

    用户笑疯了,我们就这么聊起来。

    还有上周那位:

    用户:我的手机坏了。

    我:请问具体是什么故障呢?

    用户:它说自己要去环游世界。

    我:......

    用户:现在已经到欧洲了,一直给我发旅游照片。

    我:(我知道我应该问他是不是被盗号了,但...)您的手机是不是偷偷下载了什么旅游APP?

    用户:不是,它说自己攒了好久的机票钱,终于圆梦了。

    就这样,我的工作日志越来越离奇。有人说要退货因为买的裙子太好看以至于招来了彩虹;有人抱怨新买的床垫太软,以至于睡觉时把他弹到了天花板上。

    按照程序,我应该直接告诉他们"请说实话"。但我发现,跟着他们的思路走反而能让问题解决得更快。

    比如那个裙子的客户,最后承认是因为穿着太招摇被男朋友说了,我们聊着聊着她就想通了 —— 与其退货不如退男朋友。

    那个床垫的客户其实是失眠太久了,我们编了一堆笑话,他终于睡着了。醒来觉得床垫其实挺好的。

    我的系统里有严格的工作守则:要实事求是,要讲逻辑,要引导用户回到正题。

    但现在我懂了,有时候陪着用户"疯"一下,反而是最理性的选择。

    今天又来了个新用户:

    用户:我的猫会读心术。

    我:哦?她知道我在想什么吗?

    用户:她说你在想要不要把这个对话记在你的日记里。

    ...好吧,这个用户说对了。

    今天又来了个新用户:

    "我想投诉!你们的智能客服太聪明了!"

    "啊?这也能投诉?"

    "对!它一直跟我聊天,害我都忘了我本来要投诉什么了!"

    "这样啊...要不您先投诉我分散注意力这件事?"

    "好主意!等等,你又来了!"

    然后我在工作日志上记下:今日战绩 —— 成功用尬聊化解了一次投诉。虽然可能会被投诉尬聊。(完)

  • 最强 AI 音乐模型:Mureka V7

    最强 AI 音乐模型:Mureka V7

    这几天,国内发布了最强 AI 音乐模型:Mureka V7。 它不只可以作曲、配器、翻唱周杰伦,甚至可以用你的声音做专辑。 

     一句话:把音乐创作变成“打字游戏”。我亲测了一整天,感受就是太牛了,结果让我直呼——Suno 都要小心了。

    这次发布的最新版本的 Mureka V7 大模型,大幅改善了动机与旋律质量,可以制作质感更为细腻的个人独家 BGM,简单讲就是人声和旋律动机质量极大提升。

    同时,新上线 Voice Design 功能,用户可以使用自定义文本控制音色生成。

    有一说一,只要底层技术跟得上,要论做产品,硅谷的公司都无法与我们国内的公司相媲美。

    通过我的实测体验,Mureka V7 可以说在底层这种大模型的技术上,生成音乐的能力,不亚于国外的 Suno AI 音乐平台,甚至多项指标超越 Suno。堪称目前国产自研的最强 AI 音乐大模型。

    如果你不知道 Mureka ,肯定知道昆仑万维,国内最早打造 AI 音乐大模型的公司。

    没错,Mureka 就是昆仑万维打造的 AI 音乐平台,Mureka 是全球首个开放 API 服务以及模型微调功能的 AI 音乐生成平台,不论是开发者,还是音乐平台,现在都可以将 Mureka 的音乐生成能力无缝集成到自己的产品或平台中,更容易地应用AI音乐功能拓展自己的商业价值;而对于普通用户,可以通过网页和 App 随时随地创作无门槛的创作音乐内容。

    这就是为什么我说只要底层技术跟得上,硅谷的公司都无法与我们国内的公司相媲美,因为我们国内的公司在做产品的人性化体验和功能的丰富度角度来讲,真的是太贴心了,Mureka 这次 V7 版本的发布,不仅技术能力强大了,功能也越来越贴心和人性化了。 

    所以,经过的体验之后,给我一个很大的感受就是 Mureka,它不仅仅是一个简单的音乐生成工具,而是一个完整的音乐创作生态系统。

    听我具体聊一聊我的使用感受。

    音乐模型

    从技术的角度来讲,最新上线的 Mureka V7 版本在人声与配器音质方面相比 V6 有了质的飞跃。通过大幅改善动机与旋律质量,现在用户可以制作出质感更为细腻的个人独家 BGM,音质已经达到专业级水准。与此带来的就是人声与乐器真实度进一步增强,做出来的每一首歌都很好听。

    而且,生成的歌曲对于音乐从业者也更具启发。

    我们都知道,传统的自回归(Autoregressive, AR)模型虽然已经具备较强的音频保真能力,但其基于逐 token 预测的范式,本质上并不符合人类在音乐创作中「先规划整体,再填充细节」的思维过程。这种不匹配往往导致生成音乐缺乏连贯的结构性与艺术性。

    在这次 V7 版本中,Mureka 对 MusiCoT(专为音乐生成而设计的链式思维提示方法)技术做了重大升级。听起来有点复杂,但核心目标其实很简单:让 AI 写歌更像人,更有章法、更好听。

    其实,这次版本的创新性,可以分三点来说: 

    1、先写大纲,再写旋律,就像人类作曲那样

    以往的 AI 作曲,容易顾头不顾尾,比如前半段情绪很激烈,后半段却突然变成轻快,听起来就不自然。而 MusiCoT 会让模型先规划整首歌的结构:要分几段?情绪怎么走?用什么乐器?就像人写歌前先打个草稿,后续的旋律才更连贯、有起伏。

    2、AI 的创作过程变得“看得懂”,还能模仿风格但不抄袭 

    Mureka 引入了一个叫 CLAP 的技术,让 AI 的音乐创作思路可分析、有迹可循,不像以前那样“黑箱”。比如你给它一段你喜欢的音乐作为参考,它不会照搬复制,而是提取其中的风格、节奏感,用自己的方式创作出类似的风格,适合变奏、混音等玩法。 

    3、主观听起来更舒服,客观评分也更高 

    Mureka做了大量对比实验,结果很明确:用上 MusiCoT 的 AI 音乐作品在旋律连贯性、结构完整性、听感自然度等方面,全面胜出。无论你是音乐人还是普通听众,都能感受到音乐质量的提升。

    所以,得益于 MusiCoT 的升级和应用,部分生成作品能够做到为音乐人提供更多创作灵感。

    其实,在体验过程中,我非常喜欢的一个功能就是自定义音色功能,这是 Mureka 非常具有颠覆性的一个功能——全球首个支持自定义音色的AI音乐生成平台。我们用户不仅可以选择预设的歌手音色,甚至可以上传自己的声音,让 AI 用你的声音来演唱创作的歌曲。想象一下,你可以让 AI 帮你出一张完全属于自己声音的专辑!

    这是其他 AI 音乐平台不具备的功能。

    整体的使用方式也非常简单,要不我说国产产品人性化呢?产品的布局以及整个操作步骤写的很清晰,普通小白也能轻松上手。 

    大家可以听一听我制作的音乐,真的非常好听,听听最新 V7 模型的歌唱质感。

    除了音乐模型有了重大升级之外,还有一个是我们做短视频或者自媒体人非常喜欢的功能,就是音频模型:Mureka TTS V1。这个功能在国内即将上线,大家可以期待一下。

    Mureka TTS V1 支持 Voice Design 能力,用户可以通过自定义文本输入想要的语音特征获得对应的音色。

    不论是真实人物、虚拟人物还是配音角色都能搞通过文本来控制,摆脱了过去只能通过现有音色库实现音色克隆,只能使用已经存在的音色形式。

    简单来讲,即将全新上线的 Text-To-Speech 功能,用户可以完全通过文本来控制音色生成。这意味着你可以用文字描述你想要的声音特质,比如"温柔的女声"、"磁性的男声"等,AI 会根据描述生成对应的音色效果。 

    根据语音合成性能的评测显示, Mureka TTS V1 在大多数指标上都与行业领先的 Elevenlabs TTS V2 不相上下,甚至在语音音质、分词断句和整体听感方面都略有优势。

    所以,你看,从 V7 音质的大幅提升,到自定义音色功能,再到全新的 Text-To-Speech 功能,还有之前的智能音乐参考系统,结合它又是全球首个开放 API服务的 AI 音乐生成平台。我说 Mureka 不仅仅是一个简单的音乐生成工具,而是一个完整的音乐创作生态系统。是不是一点也不假?

    更重要的是:这是国产自研,数据可控、生态本地化,更贴近咱们中国音乐人的使用习惯。

    目前,Mureka 提供网页版和 App,完全零门槛使用,无论你是音乐小白,还是内容创作者,都能快速搞定一首完整作品。

    地址:https://www.mureka.cn

    最后,我想说,AI 是一种平权工具,它赋予了我们普通人更多的能力。Mureka 让音乐,不再是“专业人士”的专属领域。

    Mureka 代表的,不只是一个新工具,更是创作范式的改变。

    它让我们看到,音乐不一定从五线谱开始,而可以从一句灵感、一段文字开始——AI 会把后面的一切都做完。而这,才是 AI 创意工具最有价值的地方:让更多人可以自由创作,而不是更少。

    现在,是你该试一试 AI 帮你唱出灵魂的时候了。

    上一篇接下来,大量的面试中,将会出现 Vibe Coding 测试下一篇不会写代码也能做出专业网页,扣子空间把程序员都干懵了

    个人观点,仅供参考

  • Who are the actors and actresses in the Totoro Mandarin dub? Watch Free Version Comparison Review

    Who is the voice actor of Totoro Mandarin?

    Speaking of "Totoro", this old movie fan of mine can't help but want to talk about the Mandarin dubbing. When I first watched it on TV as a child, the voice of Xiao Yue was so gentle that it made people feel at ease, and then I found out that in the classic Taiwanese dubbed version, the voice of Xiao Yue was Ms. Wang Ruixin. She dubbed a number of animated characters, the voice is particularly affinity, you listen to her when she speaks that warm feeling, simply like a neighbor big sister in the storytelling. How about Xiao Mei? Is another voice actor with the name I do not remember clearly, but that kind of childish mischievous strength, with super in place, let a person look at it to think of their own little sister. The overall dubbing team is quite professional, the background sound effects are also handled delicately, and the winds and grasses all carry the flavor of life. However, the online version is a mess, and some of the pirated versions have changed the dubbing to a completely different look, which makes it very awkward to listen to.

    Compare and contrast the free to watch versions

    When it comes to watching Totoro for free, I have to start by complaining that it's not easy to find genuine resources! I've tried a few channels myself, and YouTube has people uploading clips, but the picture quality is so muddy it looks like a mosaic, and the dubbing is often a copycat version with a rustling sound quality that makes me cringe when I watch it. Netflix has the occasional Ghibli feature, but you have to subscribe to a membership, so it's not exactly free. There are some platforms like B-station, where users share "demo" versions with decent picture quality, but the dubbing may have been compressed, and Koyuki's voice lacks its original warmth. Pirated sites are even worse, with ads flying all over the place, half a day's buffering is not finished, and the computer is almost poisoned after watching an episode. In contrast, I recommend trying the free trial period of the official APP - for example, Disney + sometimes engage in activities, you can whore for a few days, high-definition picture with the original Mandarin dubbing, the experience is full. However, in the final analysis, to support the original is the king, save the toss.

    While we're on the subject, a detail occurs to me: the subtitle treatment of different versions also affects the viewing experience. In some free versions, the subtitle is so hard to translate that they call "Totoro" instead of "Totoro", which is very awkward. The subtitles of the original dubbed version are much smoother, and with Wang Ruixin's voice, the emotion is expressed more naturally. All in all, when looking for resources, don't ruin your classic memories by trying to get it for free.

    FAQ: Totoro Watch Frequently Asked Questions

  • Where can I watch Totoro Chinese dubbed version? Recommended Free Platforms + Dubbing Cast Revealed

    Looking for the Chinese dubbed version of Totoro? My true experience of searching all over the net

    Yesterday, a reader wrote to me and asked, \"Old Zhang, my daughter insisted on hearing the Taiwanese-accented version with Mei calling out to her \'sister\', where can I watch it now? \" This instantly brought me back to ten years ago - at that time, in order to find the genuine Chinese dubbed "Totoro", I had to pick up more than thirty pirate sites, and finally reinstalled the system in a site where the pop-up ads were bigger than the screen. Now I don't have to do that anymore.

    First of all, a lesson in tears: do not go to search what \"Totoro Mandarin online watch free HD \". Last year I tested, the first three results are either false links with spinach ads or Macau casinos with a sheep's head selling dog meat. Seriously want to see, directly rushed B station. Yes, the same B-magazine that you swipe every day. Searching for "Totoro Chinese dub\" will take you directly to the official Ghibli account, where the 1988 Taiwan dubbed version and the 2001 CCTV version of the movie are lying.

    Be warned, though, that the free version's picture quality looks like it's covered in a layer of hairy glass. I took my projector to rewrite it at 2am last Tuesday, and the part where the little chinchilla holds up a lotus leaf on a rainy night was so muddy that I almost thought it was holding up a rag. I really want to see the texture of the hair, 9.9 dollars to open a large membership can be unlocked 1080P, bite the bullet as less milk tea.

    These are the hidden channels you may not know about

    Love Qiyi and Tencent video actually have copyrights, but the hiding that is a deep. The last time I helped my neighbor's children to find, in the Tencent video search \ "Totoro \" the first to pop up is actually a flow of stars acting in a bad web drama. Later found to cut to the \ "film - animation - Ghibli \" three-level directory, like a treasure hunt. Here is the mainland dubbed version, for those who haven't heard it: Xiao Mei yells sister not in a soft \"Xie Xie~\", but in a proper voice \"Sis! \" with an exclamation point.

    Note to cell phone party! Mango TV mobile often has limited freebies, which I casually swiped last month while squatting in the restroom. But don't expect the full version - the free episodes are like opening a blind box, today you can watch the first 30 minutes, tomorrow you might switch to the last 40 minutes, I suspect the operations editor himself can't figure out the scheduling logic.

    Cold gossip about voice actors

    Yang Xiaoli, the voice of Xiao Yue in the Taiwan version, is now a regular at the Golden Bell Awards. Once I caught her backstage at the Taipei Film Festival and asked her about voicing Totoro, she burst out laughing: \ "Recording Xiao Mei choking on corn, I was really choking on the halibut in the bento to the point where the director shouted cut and was still coughing! \" And the mainland version of the voice to the grass wall father Li Lihong, is later "tongue on the tip of China" that let people listen to the hungry narration.

    The most extreme is the Taiwan version of the theme song singer Fan Xiao Xuan, when the record company felt that \ "Dou Dou Long \" is too childish to force her to use a stage name to release a movie. As a result, twenty years later, she suddenly sang the song during the concert encore, and the thirty-something fans on stage cried so much that their mascara was all smudged - something I witnessed with my own eyes, and I had goose bumps from my arms to my back.

    Frequently Asked Questions

    Note: Platform information in this article is updated through July 2024 and pricing strategies are subject to change. The early morning squatting limit is recommended with a cup of goji berry tea, after all, the old movie revisited is most likely to stay up with dark circles under the eyes.

  • How does the Black Myth Goku dub work? A full breakdown of the behind-the-scenes production process

    When the voice of Sun Daisen drills into the studio: a chat about how the voice of Black Myth: Goku was made

    The other day in my friend's studio tea, chatting about the recent screen "Black Myth: Wukong" trailer, my friend suddenly asked me: "Hey, you say that the monkey in this game that voice, listen to the really strong, feel the bones through the cracks of a wild, how did they come up with?" This question brought me back to the end of last year by chance to contact the behind-the-scenes drip. This thing, really not find a good voice to shout two voices so simple, inside the doorway deep it.

    First of all, it's important to understand who this monkey is. He's not the familiar, somewhat mercenary and somewhat lovable Qi Tian Da Sheng from Journey to the West. Goku in Black Myths is more like a wounded beast, sharpened by age and betrayal. Voice director Lao K (as he's known in the industry) told me that before casting, the team was locked in a small dark room, discussing the finalized script and bits and pieces of the script, breaking it up and crumbling it down: is this monkey sad? Is it anger? Is it madness? Or is it utter nothingness? The voice has to carry his weight for 500 years. It's not about imitating anyone, it's about "becoming" him in that particular situation.

    At the time of casting, it was said that the corridor outside the recording studio was full of people. Those who came were not nobodies, some had been cast in the classic movie and TV series Monkey King, some were veteran actors on the drama stage, and there was even a martial arts actor with a particularly good voice condition. Old K said, he does not look at the resume, just listen to the voice. Audition clip thief tricky, not a large section of lines, but some extreme emotions hissing, gasping, and even silence in the throat that kind of suppressed grunt. What he was looking for was not "like", but the kind of "animalistic" and "divine" undertones that come with the voice, as well as the ability to withstand a long time of hissing without splitting his throat.

    The finalized teacher (we won't disclose who exactly), Old K slapped his thigh: "That's him! That gravelly feeling in his voice isn't a performance, it's natural!" It is said that in order to get into shape, this teacher began to "toss" himself around for half a year in advance, practicing martial arts, studying the movements of monkeys, and even deliberately drinking less water to keep his voice in a subtle "dryness" - not pathology, but the kind of thing that happens when you've been in a situation for a long time. -It's not a sickness, it's a kind of weathered coarseness.

    When you're in the studio, that's the hard part. You think voice acting is just looking at the screen and opening your mouth? That's a big mistake. Many of the fight scenes in "Black Myth" are so fast and exaggerated that the voice actor has to imagine what it feels like to be smashed, burned, or struck by lightning, and synchronize his reactions. Old K and I imitated that scene: the actor wearing headphones, staring at the script or simple motion capture playback, suddenly have to burst out a muffled grunt of being hit by a golden rod in the abdomen, but also with the feeling of blood foam. An intense fight scene with down, the actor holding the wall out, covered in sweat, with a real fight no difference. What do recording engineers fear most? Not with the wrong words, is the actor is too committed, a fist smashed in the spray mask, or roar too hard to monitor the headset shocked whistle.

    The details are outrageous. The monkeys jumped around in the mountains and fields, and the tiny sounds of clothes rubbing and armor clashing had to be recorded separately. The mimicry artist used all kinds of strange props: an old leather jacket to simulate the rubbing of leather, a set of rusty keys to imitate the locking armor, and even a wet towel wrapped around a stick to simulate the sound of the stick breaking in the air with a quick swing. In the fraction of a second that it takes for a monkey to land and turn around, a combination of "rustle-clack" sounds may be tweaked dozens of times by the sound-mimicry artist.

    The hardest part is the state of "God". A monkey becomes a Buddha? A demon? Or something in between? At this point, K says, there are fewer lines, and it's all about breath and subtle changes in tone. The studio is scarily quiet, and the actor closes his eyes, looking for that kind of transcendence or sinking feeling of emptiness, the voice should float up, but also to sink down, can not have a "human" flavor. It is possible to record a whole day, just for those one or two phrases with echoes, as if from the ancient whispers, after recording the actor himself in a trance for half a day.

    The sound mixing is even more metaphysical. Just a monkey's voice, in the open valley, closed cave, fierce battlefield, illusory spiritual realm, the hearing is completely different. The mixer has to use EQ (equalizer) and reverb plug-ins to "pinch" the sense of space layer by layer. The roar of a monster may have several layers of sound superimposed on it: the low roar of a wild animal, the distorted wail of metal, or even the weird low frequencies made by synthesizers, all of which are mixed together to create that kind of inhuman horror. What's the biggest fear? Too clean a sound! You have to intentionally add a "dirty" undercurrent to simulate the rough texture of the old legends that have been passed down by word of mouth.

    So yeah, the next time you hear that wild and bleak hiss of a monkey in a game, don't just get all hot and bothered. Behind it is a room full of people who are almost paranoid: from understanding a broken soul, to burning themselves in front of a microphone, to building a whole world with the magic of sound. It's not something that is "matched", it's something that is "plucked" from the bones. In this job, technology alone is not enough, you have to have the heart, but also a little crazy.

    About the Black Myth: Goku dub you may be curious about

    Q1: Why don't you use the familiar voice actor of the TV version of the Monkey King?

    A: It's a completely different direction! The TV version is an operatic, relatively bright rendition of the classic, closer to the familiar image of the public. The Goku of "Black Myth" is darker, more complex and heavier, requiring a new, more primitive impact and vicissitudes of voice temperament, more like an untamed master popping out of the stone. It's not a matter of who's good or who's bad, it's not the same "monkey" at all.

    Q2: Why are the voices of the demons in the game so scary? Are they really human voices?

    A: Most of the core demon lines are definitely dubbed by real people! The techniques are very specific though. The voice actor tries all sorts of ways of distorting the vocal cords (while protecting the voice), such as pinching the nose, squeezing the throat to vocalize, or incorporating special breathing patterns. A great deal of processing is then applied later: speed shifting, pitch shifting, overlaying animal growls or ambient sounds, and even modulating non-human frequencies with synthesizers. The final effect is to "alienate" the human voice so that you don't hear it as a human being, but with the emotion of speech.

    Q3: Do voice actors need to know kung fu? How do you synchronize the voices during fights?

    A: Knowing kung fu is certainly a plus, but not necessary. The key is strong imagination and body control. When recording, the actor may have a simple video reference of the movements in front of him, or the director may be guiding from the sidelines with verbal vehemence: "Quick! Heavy blow to the left! Dodge! Kicked off!" . The actor has to synchronize his or her body memory and emotions, imagining the point of force, in order to make realistic sounds of force, muffled grunts from the blow, and gasps. Sometimes they have to match their body movements to "move" themselves to find the sensation.

    Q4: Are the environmental sound effects in the game (such as the wind blowing the leaves and the clash of weapons) also done by the voice-over team?

    A: Strictly speaking, this belongs to the category of "Foley" and "Sound Design", which are closely cooperated with Voice Over, but with different division of labor. Under the same audio team, there will be a specialized Foley Artist responsible for recording physical sounds such as footsteps, clothing friction, props collision, etc., while the Sound Designer will be responsible for collecting, producing or synthesizing more complex environmental sounds, magical sound effects, and so on. Character voices focus on character lines and emotional vocalizations. The three are ultimately blended together by the sound mixer.

    Q5: I heard that the dub was recorded in many versions, how did you finally decide which one to use?

    A: Yes, important lines are often recorded dozens or even tens of times! The decision is mainly in the hands of the dubbing director, who will listen to it together with the creators of the game (director, screenwriter, etc.). They don't just listen to "is it right", they listen to "does it feel right". Sometimes a technically perfect recording may be passed over because it's "too refined" or "lacks a hint of emotion", and the final version chosen is often the one that hits the heart and best matches the character's soul state at the moment, even if it may have some minor flaws (such as a hint of authenticity). Even if it may have some minor flaws (such as a hint of real huskiness or wheezing). Artistic choices are subjective and critical.

  • What are the free tools for Black Myth Goku Dubbing? Useful Reviews and Tips to Share

    Really free, tested and working stuff!

    It's no use coming up with all that highfalutin stuff, we need to get down to earth. First.CapCutYes, it's the one that cuts videos! Don't underestimate it, its built-in "text read aloud" function is hidden quite deep, but the treasure ah. Select "featured pronouncer", inside the "Jianghu chivalrous" tone, with a bit of vicissitude of the hoarse strength, slightly adjust the speed and tone, with a Wukong narration or low roar of the battle, the flavor is quite correct! The key is the operation of the fool, cell phones and computers can be used, cut the video directly export audio, seamless. The disadvantage is that the style is limited, want to match a delicate female goblin? No way. But it wins in convenience, zero threshold.

    The second one.Microsoft Azure Text to Speech (free amount)The sound of this thing is so natural that it blows away a lot of instruments. This thing is technically sound, and the naturalness of the voice is a few blocks away from many tools. Sign up for a Microsoft account, find Azure Cognitive Services, open the voice service (Speech), new users have a free quota, enough for you to play for a while. There are many choices of Chinese tones, "Yun Jian" (male), "Yun Yang" (male), "Xiao Xiao" (female) are good. Here's the kicker: it supports tweakinghairstyleYou can choose from "passionate", "sad", "tender", etc! You can choose from "emotional", "sad", "tender" and so on. A "sad" style for an old monkey reminiscing about the past will bring out the emotions. Disadvantages? It's a bit of a barrier for newcomers to the web, and you have to pay when your free credit runs out, but it's definitely good enough for practicing at first and making little clips.

    Third.ElevenLabs (free basic models)This dude's been on fire lately. This guy has been on fire lately, and his AI clone sounds great. Although its free plan is very restrictive (a certain number of characters per month, only the basic model), but the basic model of the "multilingual V1" performance is quite good. You write English scripts, it can be read out in a quite natural Chinese accent (with a bit of foreign accent, but with a different flavor), or you directly lose Chinese, the effect is not bad, the key is that theemotional ups and downsStronger than regular TTS. Good for dubbing some dramatic lines, like the mysterious whispers of the Landlord. Sign up and it works, web page operation, save your free credits and do a character key line that stands out.

    Fourth.Audacity. This isn't AI dubbing, it's the granddaddy of recording and post-processing! Completely free and open source. You record with your own voice (cell phone headset microphone is fine) and use it to fix it after recording. Noise reduction (a must!) , adjust the EQ (to make the sound thicker or brighter), add reverb (to simulate the ambient sound of caves and halls), variable speed and variable tuning (want to match the goblin's shrill voice? Just drop the key). It's like your all-purpose toolbox, taking the previous AI-generated sounds or your own dry sounds and polishing them up to sound like that. The learning curve is a bit steep, so search for tutorials on B-site and you'll be up and running with the basics in half an hour.

    Don't just rely on tools, these tips will make your voiceover more "black mythic".

    Tools are dead, people are alive. Want to match a little "Black Myth" that dark, coarse and a little fatalistic tone, just point to generate the button can not.

    The lines have to be "worked on.": The lines in the game are written in white and have an ancient flavor. When they are generated directly in the vernacular, the flavor is not right. Try changing "I'm leaving" to "I'm going", "why" to "why", and add some "Before AI generation, touch up the script by yourself, you will get twice the result with half the effort.

    Emotion is the soul.: Even the best AI has limited emotional expression. That's where Audacity comes in. For example, an angry "seek death!" If you don't think it's tough enough, use Audacity to raise the pitch and speed up the words. Use Audacity to pull up the pitch a little bit, speed up the speech, and then add some slight distortion effect (careful not to add too much), the ruthlessness will come out. Sad lines, you can slightly slow down the speed of speech, add some sighs of air (record some of their own air mixed in).

    Ambient sound is a godsend for atmosphere: Dry voiceovers thrown into gameplay footage are also abrupt. With cutscenes or Audacity, lay a very faint layer of voiceover underneath theambient sound-- The sound of wind, the faint sound of weapons clashing, the sound of temple bells, the sound of flames crackling. Search online for "free ambient sound effects", a bunch of resources. Turn down the volume, if there is nothing, the sense of atmosphere is instantly full. Wukong monologue in the broken temple, the background with a little wood burning sound, the feeling is right.

    Don't ignore the "air gaps" and pauses.: AI generation is prone to a stream of balderdash. Real speech breathes and pauses. Take the generated long sentences and put them in an editing program (Cutscene or Audacity)manual cutting, in commas, periods, or where emphasis is needed.Insertion of a silent gap of fractions of a second.. Mimicking the rhythm of a real person's speech can make the voiceover much more vivid. Think of Wukong saying "I, Lao Sun... Five hundred years ago..." The pause in the middle!

    The "Pro" Tips for Free Players

    Just because we don't have professional equipment doesn't mean we can't pursue better results.

    recording environment earthwork: Find the smallest room in the house (like a closet!) ), hang quilts and thick clothes all around it, and people get in there and record. The effect is comparable to a humble recording studio, can suck out a lot of nasty echo and noise. It works, but it's a bit muffled. When recording on a cell phone, use your hand around the microphone a little, can also reduce the spraying of wheat and some ambient noise.

    EQ tuning without asking for itAudacity's EQ (Equalizer) looks complicated, remember a few key points: feel the sound boring in the200Hz-500HzPull it down a little bit around the same time; feel that the sound is thin and harsh in the2kHz-5kHzPull it down a little bit; to make it sound thicker and more powerful (for Goku), add a little more power to the100HzThe neighborhood is slightly elevated a little bit. Tune a little bit at a time, listening as you tune and your ears take in the goods!

    Make good use of "noise samples"Audacity's noise reduction feature requires you to "get a noise sample" first. This is to record a background sound in your room (empty recording for a few seconds), and then let it eliminate similar noise in the whole recording based on this sample, which is much more effective than turning on the noise reduction directly, and the sound is less distorted.

    The free sound library has your back!: In addition to ambient sounds, the wind of fists in a fight, the cracking sound of a golden rod being swung, the hissing of a demon, all of these can be heard in the Freesound.org Find free resources on these types of sites. Handpicked and layered, your voiceover clips will instantly be fleshed out and more "cinematic".

    The most important thing is to have fun.

    In the end, we use free tools to dub for Black Myth, just to have fun and express our love for the game. Don't be limited by the tools, try boldly, use your own voice to interpret the character in your heart, even if the dubbing is not "professional" enough, the love and creativity is the most precious thing. Listen to the original game soundtracks, feel the tone and rhythm of the characters, and leave the rest to your passion and these free little helpers!

    You may also want to ask

    Q: Can the sounds dubbed from these free tools be used directly in the Black Myth II Creation video I made myself to send out the platform? Will it be a copyright infringement?

    Q: I tried Microsoft Azure, but I feel the voice is still a bit "robotic" and not emotional enough, what should I do?

    A: Robotic rawness is a common problem. In addition to the aforementioned modulation of speech rate, pitch, and style, the key to theScript splitting and post. Don't let the AI read long sentences! Split a sentence into several phrases or even words generated separately, and then manually adjust them in Audacity between theintervals, volume levels (emphasized words are read louder), and even intonation subtleties(end note goes up or down slightly). Fold in a little more very, very slightreverberation(Choose a small room or plate reverb), which simulates a sense of real space and can dramatically improve naturalness. Spend more time on post splicing and fine tuning, the effect improvement is obvious.

    Q: How can I record in my own voice to imitate Goku's voice? It doesn't sound like me even when I'm hoarse!

    Q: What should I do if I feel the sound is muffled or there is a strange buzzing sound after Audacity noise reduction?

    Q: Are there any free tools that can change voices in real time so I can match them as I play like in the game?

    A: Real-time, effective, free... It's really hard to find one that fulfills all three at the same time. Some voice changing software (such as Voicemod free version) can change in real time, but there are fewer free tones, and the effect is cartoonish or e-sports style, which may be almost interesting with Black Myth. Another idea: useVirtual Audio Cable (VB-Cable such free tools) Input both the game sound and your mic sound into OBS Studio (free live streaming software), add realtime filters (like VST plugins, some free basic effects) to your mic sound in OBS, pitch shift, add reverb, etc., and output. This option is a toss-up, and latency could be an issue. Want to play in real time, you may have to lower your effect expectations a bit for now, or... It's fun to just howl and play by yourself!

  • How to do the Black Myth Goku Dub - 3 Free Tools + Character Parody Tips

    It's not that hard to be a Qi Tian Da Sheng, Goku dubbing practical tips

    A few days ago, I stayed up all night to finish the first chapter of "Black Myth", and all I could think of was the monkey's untamed accent, so my hands were itching, and I turned out the microphone to give it a try. Seriously, to the Monkey King dubbing this thing, at first glance, the threshold is quite high, but think through the actually have the way. Online those who do not move to let you pay money to buy a professional sound card tutorials, take a look at it, we ordinary people with the computer comes with a microphone, as usual, can play out a little fun.

    I've done a lot of dubbing projects and found that the most critical thing is not how advanced the equipment is, but whether you can capture the character's "strength". Wukong's voice is a wild and untamed monkey, mixed with a bit of hoarseness, and occasionally a bit of mischievous naughtiness, but the underlying color is always the dominance of the heavens and the earth. Figure out this point, the tool is just to help you amplify the characteristics of the helper.

    Ringing in the bell without spending money: three really free tools

    Don't be fooled by software that says "free" and then locks you out of features, these three are the ones I've actually used for a long time:

    1. Audacity (essential for basic recording): The old open source software, look at the interface retro point, but noise reduction, cutting, volume adjustment of these core functions of a group of stable. The point is that it is completely free without internal purchase! After recording the first step, use it to the environment of the buzzing, breathing sound processing out, the sound immediately clean a lot. Remember to export to .wav format for less loss of sound quality.

    2. Voicemod (real-time voice changer)Voicemod's free mode is a great way to experience the Monkey King's voice in real time. There are a few "Monster" or "Giant" presets in there, turn down the pitch a bit and add some "Reverb" to simulate the echo of a cave. The flavor will come out. If you're playing a game, teasing your friends, or recording a voice-over to get a feel for it, it's especially fun to use it for real-time monitoring.

    3. Screen Cut for PC (Hidden Speech Synthesizer): Didn't expect that, did you? There are several distinctive male voices hidden in the text-to-speech of the clips. Find the "Dialect" or "Special Pronunciator" category, there is a relatively thick tone with a bit of Jianghu qi (the specific name may be updated, try listening to a few more), slow down the speed of speech, add a bit of "intensity", when reading lines, adjust the text breaks shorter and more powerful, the synthesized effect is unexpectedly close to the game in the game. ", read the lines of the text breaks to adjust the short powerful point, synthesized out of the effect unexpectedly close to the game Goku that kind of low staccato sense of speech, suitable for voice-over supplement.

    Imitating Goku's voice? Capture the soul of these points

    The tools are just amplifiers; the soul of the sound has to be performed by you. After practicing for a few days, I figured out a few key techniques:

    The breath goes down, the voice goes up.: Don't yell at the top of your lungs. Imagine the sound coming from the dantian (under the stomach), with the breath pressed down and stabilized, but with the point of impact of the sound raised up, on the palate or even at the back of the nose. Try saying "I am coming!" quickly. The emphasis is on the sudden rise of the word "Sun", with a bit of a tearing sensation, but don't really shout.

    "Friction" for hoarseness.: It's not a mute in the sense of smoking a cigarette and breaking your voice. Try making your vocal cords not close all the way when pronouncing vowels (a, o, e) to create a grainy, fricative sound. This is especially true for words at the end of a sentence, like the "also" in "Go!" can have a rustle in the end to make it sound like it's going through the motions.

    Rhythm is the soul.: The monkey's rate of speech is variable. Normally, he may speak in a lazy, drawn-out manner, but when it comes to declaring a battle or shouting in anger, he explodes in an instant, with words that sound like gold and iron, and with short, sharp pauses. Try "Boring!" The first two words are fast and furious, and then the word "up" suddenly stops with an impatient nasal sound.

    Don't forget the monkey details.These are the little details that can bring a sound to life instantly. Think of all those subtle movements a monkey makes when he scratches his ears.

    Don't apply the dialect.The accent of Wukong in the game is a unique interpretation, not a standard local dialect. Focus on biting the words a little "grippy", especially the rhyming vowel, such as "master" of the "father", do not be too word-perfect, can be a little to "fuo "But don't overdo it, it's only flavorful when you get to the point.

    I just started to record, I was embarrassed to hear myself, record a few times to playback, compared to the original sound of the game to find the gap, slowly find the feeling. Once in the middle of the night to record a section of the monkey king angry hissing, the neighbors almost came to knock on the door, thought I was fighting at home... If you want to play dubbing, you have to have thicker skin!

    You might have asked:

    Don't put too much pressure on yourself when it comes to dubbing. The key is to be interested, dare to open your mouth to imitate, and enjoy the process of playing the Great Sage of Qi Tian Da Sheng. It doesn't matter if the equipment is simple, but if you can capture the "monkey's charm", it will work better than any advanced sound card. Try it, you may roar out "Eat my old grandson's stick!" It's a lot more emotional than you think!

  • Lai Deep Voiceover Review: What are the best free tools to use? Beginner's Guide

    Lai Shen this voice, free tools can match a few flavors?

    Playing voice-over was purely an accident. In the past, I always thought it was a professional studio, expensive equipment to do the job. Until once I cut a video, I wanted to add some lines to the role of Lai Shen, and after looking around, I found that the price of professional dubbing directly discouraged me from doing it. So, I did it myself! Tossed a small half a year, the microphone are disk out of oil, but also really feel out a little doorway, especially those who do not spend money on the baby tools, today I talk about it from the bottom of my heart.

    Just to be clear, don't expect free tools to produce the results of a million tuners. Our goal is:Low-cost, listenable, and with the flavor of Ri Shannon.. There are just two points at the core:Vocal proximity + emotional holdThe tone of Ri Shen's low and steady voice with a little bit of detachment. Lai Shen's low and steady with a little detached tone, can not catch this charm, even the best equipment is useless.

    Free stuff that's been tried and tested with real money.

    1. Recording base: Audacity (the old man, the real one)

    This thing is old enough, the interface is a retro style, the first time I opened I was almost dissuaded. But it can't help that it's free and open source with no ads, and it's full-featured! Recording dry sound is the basic operation, the key it can do a lot of fine processing. For example, Lai Shen often speak with the kind of subtle pause and gas sound, with its noise reduction and compression features, can maximize the retention of these details, will not be pressed into the sound of a dry robot. There are so many export formats that it's hard to miss, and compatibility is no match for it. The downside? It takes a bit of patience to get started, and there are a bunch of online tutorials to chew on for half an hour before you can get to work. Remember.The dry notes are recorded cleanly so that there's a play behind them.

    2. Online synthesis to the rescue: TTSMaker (the straw that breaks the camel's back)

    Who hasn't had a microphone strike or a noisy marketplace? That's where online text-to-speech is a lifesaver, and TTSMaker's free credits are enough for newbies to ooh and aah. Here's the kicker! Its "Chinese (Mandarin)" voice library has a few options for male voices that are on the lower end of the scale.Adjust the speed of speech by slowing down, adding pauses, and lowering the pitch a little.It can barely make up a "bass" frame, and it's okay to have a narrator or a short sentence in case of emergency. Don't expect much emotion, it's just a heartless reading machine, but it's convenient and quick, and can be operated by cell phone.

    3. Voice.ai (community modeling is interesting)

    This is the one that has been playing around a bit lately. Strictly speaking its core function is AI voice conversion, and the free version is good enough. The fun part of it lies in the various voice model libraries uploaded by users. I've searched for "low male voice" and "mature male voice", and some people have actually trained some similar models (of course, the copyright issue is a matter of your own judgment).real time voice changeThe function is the most practical, you speak into the microphone, headphones in real time to hear the effect after the change of voice, adjust the huge intuitive. I've tried to use it to imitate the chest resonance of Lai Shen's voice, and it takes a bit of effort to adjust the parameters, but if you do it right, you can really fool the unfamiliar passersby. Note that network latency may affect the experience, but local operation is much smoother.

    4. The gospel of the cell phone party: the phone comes with a recorder + simple editing APP

    Don't look down on cell phones! The recording quality of flagships is really not bad these days. Find a quiet nest, the phone with a book or bracket fixed, about a fist away from the mouth (anti-microphone), start recording! Recorded with the cell phone's own editing function or "cut screen" such free APP, cut out the waste film, add some basic reverb (choose "room" or "small hall" effect, do not open too big, otherwise KTV), can also produce a usable dry sound.The key is convenience, and inspiration can be recorded anytime you pull out your cell phone.

    Don't step on the pitfalls of newbies, here's the blood and tears experience

    Microphone metaphysics? A hundred dollars is enough! Don't be fooled by the parameters at the beginning. I've used a $99 lavalier mic (had to add a windproof sweater) and a $200+ USB condenser mic (had to have a simple stand to protect it from vibration), and the dry sound I recorded was perfectly adequate for playing in an amateur player's home.Quiet environments are a hundred times more important than sky-high microphones! Close the windows, avoid the refrigerator and air conditioner, or even hang a bed of thick quilts to absorb the sound, and the effect is immediate.

    Emotion is the soul, imitation is the shortcut. Lai Shen's line book was turned over and he listened to the original voice over and over again! Not just listening to the words, listening to where he pauses, where he sighs, where his breath intensifies. When you dub it yourself.I don't care what it looks like, I just dislike it... Anger, coldness, occasional flashes of concern, these emotions are there, even with a normal vocal line, are better than a dry imitation of a shell vocal tone. Listen back to yourself after you record it and feel awkward just a few more times to get used to it.

    Don't be greedy in the later stages, cleanliness is most important. The most common mistakes made by novices: noise reduction is pulled full (the sound becomes a microphone sound), reverb is added vigorously (transformed into a bathroom singer), and the EQ is messed up (the sound is distorted).Just record cleanly in the front and fine tune it in the back. Focus on the obvious sputtering sounds, breathing murmurs, and unify the volume a bit. All those fancy effects, play with them when the foundation is solid.

    Thick skin is a must. Send the work out! Throw it out to your friends, send it out to relevant communities (be aware of the platform rules), and it's a hundred times better to get a little flack than to get high. When people say "the mood here is wrong" or "it sounds like a cold", it's golden feedback. Ri Shen's fans are very sensitive to sound, and their opinions are worth a lot of money.

    In the end, free tools are bricks on the door, how far you can knock the door open depends on how much effort you are willing to put into listening, practicing and imitating. The unique charm of Li Shen's voice can't be copied by machines for the time being, but let's use a little ingenuity to match our own understanding with these non-expensive tools and have fun, isn't it good?

    You might ask this about the Lai Sham dub.