VOCALOID(日语:ボーカロイド/ボカロ,中文:博歌乐,英文简称:VOCALO)是由日本Yamaha株式会社开发的电子歌声合成(Singing Synthesis)技术,以及应用该技术的软件的合称。
VOCALOID是日本YAMAHA公司自主开发的一款电子歌声合成软件,输入音调和歌词,就可以合成贴近人类声音的歌声。截至2022年12月,该程序分为VOCALOID(V1)、VOCALOID 2、VOCALOID 3、VOCALOID 4、VOCALOID 5、VOCALOID 6(VOCALOID:AI)共六代,该软件的传统拼接声库最初基于Music Technology Group(MTG,庞培法布拉大学下属机构)开发、授权YAMAHA使用的「Frequency-domain Singing Articulation Splicing and Shaping」技术,采集不同人类的声音标本,然后再制作歌声资料库(音源/声库),从而合成声音。VOCALOID:AI则使用了神经网络合成技术实现了更为自然的合成歌声。
中国民间通常称为“V家”,其也是“V+”的谐音。若要完全翻译为中文,根据词源,可以称呼为“歌唱机器人”。直译会变成奇怪的“领音半辅音(如r)”(即语音学领域中的“vocaloid”。相应地,“vocal”意为“领音”)。
仅仅输入歌词与旋律合成歌声,声音会显得机械。而VOCALOID编辑器为用户(通称“调教/校师”或“P主”)提供诸多可量化的参数,以丰富歌声的细节和情感。
现常用的编辑器中,V4中有12个参数;V5中删除XSY参数,新增AIR、EXT2个参数,总计13个;V6(6.5及以上版本)中恢复了XSY参数,总计14个;VOCALOID:AI中仅有3个参数(6.5及以上版本增加AIR为4个)。具体如下:
* 注:参数英文名前为简称,后为全称。若有两组英文名(如开口度,Opening/Mouth),则前为V4及以前版本的参数名称,后为V5及以后版本的参数名称。部分参数英文全称相同,但在V6中更改了简称,(如滑音,PIT/PB)
Yamaha started development of VOCALOID in March 2000 and announced it for the first time at the German fair Musikmesse on March 5–9, 2003. The first VOCALOIDs, Leon and Lola, were released by the studio Zero-G on March 3, 2004, both of which were sold as a "Virtual Soul Vocalist". Leon and Lola made their first appearance at the NAMM Show on January 15, 2004. Leon and Lola were also demonstrated at the Zero-G Limited booth during Wired Nextfest and won the 2005 Electronic Musician Editor's Choice Award. Zero-G later released Miriam, with her voice provided by Miriam Stockley, in July 2004. Later that year, Crypton Future Media also released their first VOCALOID Meiko. In June 2005, Yamaha upgraded the engine version to 1.1. A patch was later released to update all VOCALOID engines to VOCALOID 1.1.2, adding new features to the software, although there were differences between the output results of the engine. A total of five VOCALOID products were released from 2004 to 2006. VOCALOID had no previous rival technology to contend with at the time of its release, with the English version only having to face the later release of VirSyn's Cantor software during its original run. Despite having Japanese phonetics, the interface lacked a Japanese version and both Japanese and English vocals had an English interface. The only differences between versions were the color and logo that changed per template. As of 2011, this version of the software is no longer supported by Yamaha and will no longer be updated.(翻译时有一部分是意译,即改变了原文的语序及部分表达。)
VOCALOID 2 was announced in 2007. Due to time constraints, unlike the previous engine version, it did not have a public beta test and instead the software was updated as users reported issues with it. The synthesis engine and the user interface were completely revamped, with Japanese VOCALOIDs possessing a Japanese interface. New features such as note auditioning, transparent control track, toggling between playback and rendering, and expression control were implemented. One's breath noise and husky voice can be recorded into the library to make realistic sounds. This version is not backward compatible and its editor cannot load a library built for the previous version. Aside from the PC software, NetVOCALOID services are offered. Despite this, the software was not localized and VOCALOIDs of either English or Japanese would only possess that language version, so although Megurine Luka had an English library included, as a Japanese VOCALOID she only had access to the Japanese version of the software. In total, there were 17 packages produced for VOCALOID 2 in the Japanese version of the software and five in the English version; these packages offered 35 voicebanks between them in either English or Japanese.
Yamaha announced a version of the VOCALOID 2 software for the iPhone and iPad, which exhibited at the Y2 Autumn 2010 Digital Content Expo in Japan. Later, this version of the software was released using the voice of Yamaha's own VOCALOID called VY1.(翻译时有一部分是意译,即改变了原文的语序及部分表达。)
New technology is also being used to bring back the voice of the singer Hitoshi Ueki who died in 2007. This is the first attempt to bring back a singer whose voice had been lost, yet it had been considered a possibility since the software was first released in 2004. However, this is only being done for private use.[35](翻译时有一部分是意译,即改变了原文的语序及部分表达。)
比起以前的版本,V5拥有超过1000声的短语和超过1000的音频样本,超过100种歌唱风格预设,11种声音特效,编辑器支持VST,支持V3,V4旧版声库。
同时,工程文件格式由VSQX(V3/V4)变为VPR(V5),编辑器仍旧支持对VSQX的读取,但不再支持更早的VSQ格式。
此版本同时由原有的12大参数,调整为13个参数。增加对Attack&Release效果的支持,增加对单个音符波形本身的调整功能,支持实时音高渲染,支持由MIDI乐器进行的即时输入,最大同时包含音轨轨道数32个。取消了对Job Plugin任务插件、Cross Synthesis(XSY)的支持。
声库的部分则新增了4位声优,包含VY1日语女声以及VY2日语男声、 CYBER SONGMAN II英语男声、CYBER DIVA II英语女声。
2021年3月,雅马哈株式会社在中国大陆注册了“VOCALOID:AI”的商标。
2013年12月起,Crypton在软件更新中为Piapro Studio提供了使用其他公司推出的声音库软件的支持,Piapro Studio的性价比得到提升。
在目前(2022年)YAMAHA VOCALOID4编辑器早已停止售卖的前提下,Piapro Studio成为了性价比最高的VOCALOID3/4歌声编辑器。购买价格最便宜的初音未来 V4 中文版软件(低于700人民币)即捆绑VSTi版的Piapro Studio编辑器,可编辑各类声库(VOCALOID5编辑器定价27500日元,约为1300人民币)。
Crypton并未获得VOCALOID5 API的使用许可,Piapro Studio因此也暂无兼容V5声库的计划。Piapro Studio NT与VOCALOID声音库不兼容。
又称为“语调校”,指某些P主使用本软件中的音源在调音后生成与人声朗读相似其实还是有点唱歌的成分的部分作品,通常用于制作小剧场。