{"id":67923,"date":"2022-09-30T18:05:24","date_gmt":"2022-09-30T15:05:24","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=67923"},"modified":"2025-09-07T09:13:47","modified_gmt":"2025-09-07T06:13:47","slug":"google-trains-ai-to-speak-more-clearly-and-naturally","status":"publish","type":"post","link":"https:\/\/u1f987.com\/en\/google-trains-ai-to-speak-more-clearly-and-naturally\/","title":{"rendered":"Google trains AI to speak more clearly and naturally."},"content":{"rendered":"<p>Google will update the Speech Services text-to-speech engine on Android devices, delivering voices that are clearer and more natural-sounding.<\/p>\n<figure class=\"wp-block-embed is-type-rich is-provider-twitter wp-block-embed-twitter\">\n<div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"twitter-tweet\" data-width=\"500\" data-dnt=\"true\">\n<p lang=\"en\" dir=\"ltr\">Text-to-speech is getting a voice upgrade \ud83d\udde3\ufe0f \ud83d\udc42 <\/p>\n<p>The automatic Speech Services by Google update covers 421 voices in 67 languages to offer a more natural-sounding speaker on all 64-bit Android devices \ud83c\udf89<\/p>\n<p>Hear the difference \u2193 <a href=\"https:\/\/t.co\/LJw9faGMJC\">https:\/\/t.co\/LJw9faGMJC<\/a><\/p>\n<p>\u2014 Android Developers (@AndroidDev) <a href=\"https:\/\/twitter.com\/AndroidDev\/status\/1575214686118739982?ref_src=twsrc%5Etfw\">September 28, 2022<\/a><\/p><\/blockquote>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script>\n<\/div>\n<\/figure>\n<p>According to the developers, users won&#8217;t have to do anything\u2014the upgrade will occur behind the scenes. The update will significantly improve the quality of generated speech, particularly in terms of clarity and naturalness, they added.<\/p>\n<table style=\"width:100%\">\n<style>\ntable, th, td {\n  border:0px solid black;\n  font-family: 'Inter var',sans-serif;\n  font-size: 12px;\n  font-weight: 400; \n    color: #65687d;\n    font-style:normal;\n}\n<\/style>\n<tr>\n<th>\n<figure class=\"wp-block-audio\"><audio controls src=\"https:\/\/u1f987.com\/wp-content\/uploads\/sfg_old.wav\"><\/audio><figcaption>Example of current generated speech<\/figcaption><\/figure>\n<\/th>\n<th>\n<figure class=\"wp-block-audio\"><audio controls src=\"https:\/\/u1f987.com\/wp-content\/uploads\/new_iog.wav\"><\/audio><figcaption>Example of generated speech after the upgrade<\/figcaption><\/figure>\n<\/th>\n<\/tr>\n<\/table>\n<p>The 421 voices across 67 languages will receive a new voice model and synthesizer. The current American English voice will automatically be updated to a speech generated with &#8216;more up-to-date data&#8217;.<\/p>\n<p>The developers also showed samples of updated voices in other languages.<\/p>\n<table style=\"width:100%\">\n<style>\ntable, th, td {\n  border:0px solid black;\n  font-family: 'Inter var',sans-serif;\n  font-size: 12px;\n  font-weight: 400; \n    color: #65687d;\n    font-style:normal;\n}\n<\/style>\n<table style=\"width:100%\">\n<tr>\n<th>\n<figure class=\"wp-block-audio\"><audio controls src=\"https:\/\/u1f987.com\/wp-content\/uploads\/afs_old.wav\"><\/audio><figcaption>Portuguese (Brazil) before the upgrade<\/figcaption><\/figure>\n<\/th>\n<th>\n<figure class=\"wp-block-audio\"><audio controls src=\"https:\/\/u1f987.com\/wp-content\/uploads\/afs_new.wav\"><\/audio><figcaption>Portuguese (Brazil) after the upgrade<\/figcaption><\/figure>\n<\/th>\n<\/tr>\n<tr>\n<th>\n<figure class=\"wp-block-audio\"><audio controls src=\"https:\/\/u1f987.com\/wp-content\/uploads\/esf_old.wav\"><\/audio><figcaption>Spanish (US) before the upgrade<\/figcaption><\/figure>\n<\/th>\n<th>\n<figure class=\"wp-block-audio\"><audio controls src=\"https:\/\/u1f987.com\/wp-content\/uploads\/esf_new.wav\"><\/audio><figcaption>Spanish (US) after the upgrade<\/figcaption><\/figure>\n<\/th>\n<\/tr>\n<\/table>\n<p>The company will roll out the Speech Services update to all 64-bit Android devices via the Google Play Store over the coming weeks.<\/p>\n<p>Earlier in September, OpenAI <a href=\"https:\/\/u1f987.com\/en\/news\/openai-unveils-whisper-an-open-source-speech-recognition-system\">unveiled<\/a> the open-source Whisper speech-recognition system, capable of transcription in multiple languages.<\/p>\n<p>In August, the streaming service Megogo employed AI to provide AI-generated voiceovers for video content.<\/p>\n<p>In May 2021, Google unveiled the neural network model LaMDA, which communicates like a living human and supports casual dialogue on a range of topics.<\/p>\n<p>Subscribe to ForkLog news on Telegram: <a href=\"https:\/\/t.me\/forklogAI\" target=\"_blank\" rel=\"noreferrer noopener nofollow\"> ForkLog AI<\/a> \u2014 all the news from the world of AI!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google will update the Speech Services text-to-speech engine on Android devices, delivering voices that are clearer and more natural-sounding.<\/p>\n","protected":false},"author":1,"featured_media":67924,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,738],"class_list":["post-67923","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-google"],"aioseo_notices":[],"amp_enabled":true,"views":"11","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/67923","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/comments?post=67923"}],"version-history":[{"count":1,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/67923\/revisions"}],"predecessor-version":[{"id":67925,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/67923\/revisions\/67925"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media\/67924"}],"wp:attachment":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media?parent=67923"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/categories?post=67923"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/tags?post=67923"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}