{"id":211125,"date":"2023-01-31T11:53:46","date_gmt":"2023-01-31T10:53:46","guid":{"rendered":"http:\/\/sftarticles.wpenginepowered.com\/es\/?p=269141"},"modified":"2025-07-01T20:06:07","modified_gmt":"2025-07-02T03:06:07","slug":"new-ai-google-convert-text-music","status":"publish","type":"post","link":"https:\/\/cms-articles.softonic.io\/en\/new-ai-google-convert-text-music\/","title":{"rendered":"Make Your Words Musical: Google’s AI Brings Text to Life with Music"},"content":{"rendered":"\n

A research team at Google<\/a> has created an artificial intelligence that is capable of generating musical pieces from a written description<\/strong>. As if that were not enough, you can also transform a hum into melodies played by different instruments<\/strong>. <\/p>\n\n\n

\r\n
\r\n
\r\n
\r\n \"Google\r\n <\/div>\r\n
\r\n Google Chrome<\/span>\r\n DOWNLOAD<\/a>\r\n <\/div>\r\n
\r\n <\/path><\/path>8<\/text><\/svg>\r\n <\/div>\r\n <\/div>\r\n
\r\n <\/span>\r\n <\/div>\r\n
\r\n \r\n <\/div>\r\n <\/a>\r\n <\/div>\r\n<\/div>\n\n\n\n

This artificial intelligence follows a process very similar to that of other tools such as ChatGPT<\/a> or Stable Diffusion, which use a description or “prompt” to be able to generate images<\/a> or texts. The model that concerns us today is called MusicLM<\/strong> and although we still can’t prove it for ourselves, we can appreciate some of the results that Google itself has uploaded. <\/p>\n\n\n\n

MusicLM, the ChatGPT of music<\/h2>\n\n\n\n

The examples we can hear are pretty impressive. The fragments have a short duration (30 seconds) and first of all, they can pass for real songs, even for the most expert ears. The melodies are recreated from specific descriptions, where we can choose from the genre to the instruments. To make matters worse, MusicLM can generate pieces with descriptions as brief as “melodic techno”.<\/strong> <\/p>\n\n\n\n

Another of MusicLM’s features is that it can “Mix<\/strong>” between different descriptions, in order to create more complex songs. As an example, the AI was able to generate this audio<\/a> based on this description: “electronic song in a video game (0:00-0:15), meditation song by a river (0:15-0:30), fire (0:30-0:45), fireworks (0:45- 0:60)”.<\/p>\n\n\n\n

Additional details that indicate the time help MusicLM build a foundation<\/strong> for these “artificial songs”. As with other generative models, MusicLM benefits from a huge database of sounds and audios, which help it “train” itself to improve.<\/p>\n\n\n\n

MusicLM is even capable of simulating human voices<\/strong>, although their quality is still questionable. And if you ask them to sing in any language, it gets even worse. The feeling when listening to these voices from the digital underworld is that they pretend to sound like English, but to no avail.<\/p>\n\n\n\n

Despite Google’s advances in the field of AI<\/a>, the truth is that the company is not doing very well in the public eye. Tech giants like Microsoft and now OpenAI are overtaking Google in artificial intelligence. In fact, Google recently issued a “code red” to its employees to get them to step up their game against the threat of tools such as ChatGPT. Will Google manage to recover its position in the AI race?<\/strong><\/p>\n","protected":false},"excerpt":{"rendered":"

A research team at Google has created an artificial intelligence that is capable of generating musical pieces from a written description. As if that were not enough, you can also transform a hum into melodies played by different instruments. This artificial intelligence follows a process very similar to that of other tools such as ChatGPT … Continue reading “Make Your Words Musical: Google’s AI Brings Text to Life with Music”<\/span><\/a><\/p>\n","protected":false},"author":9211,"featured_media":211126,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","wpcf-pageviews":1},"categories":[1015],"tags":[],"usertag":[],"vertical":[],"content-category":[],"class_list":["post-211125","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/211125","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/users\/9211"}],"replies":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/comments?post=211125"}],"version-history":[{"count":1,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/211125\/revisions"}],"predecessor-version":[{"id":322395,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/posts\/211125\/revisions\/322395"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media\/211126"}],"wp:attachment":[{"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/media?parent=211125"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/categories?post=211125"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/tags?post=211125"},{"taxonomy":"usertag","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/usertag?post=211125"},{"taxonomy":"vertical","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/vertical?post=211125"},{"taxonomy":"content-category","embeddable":true,"href":"https:\/\/cms-articles.softonic.io\/en\/wp-json\/wp\/v2\/content-category?post=211125"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}