{"id":3229,"date":"2021-06-23T13:23:36","date_gmt":"2021-06-23T11:23:36","guid":{"rendered":"https:\/\/www.pschatzmann.ch\/home\/?p=3229"},"modified":"2024-07-25T11:01:18","modified_gmt":"2024-07-25T09:01:18","slug":"text-to-speach-in-arduino-conclusions","status":"publish","type":"post","link":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/","title":{"rendered":"Text To Speach in Arduino &#8211; Final Conclusions"},"content":{"rendered":"<p>In my last couple of Blogs I was comparing the following Text To Speach (TTS) libraries which are available on <strong>Arduino<\/strong>:<\/p>\n<ul>\n<li><a href=\"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/22\/text-to-speach-in-arduino\/\">SAM<\/a> Software Automatic Mouth<\/li>\n<li><a href=\"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/22\/text-to-speach-in-arduino-using-tts\/\">TTS<\/a> Text-to-Speech Library for Arduino<\/li>\n<li><a href=\"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-using-flite\/\">Flite<\/a> Festival lite<\/li>\n<\/ul>\n<p>I was hoping to find some <a href=\"https:\/\/www.tinyml.org\/\">TinyML<\/a> based implementations, but so far without success: I put this on my to-do list for some long cold winter days.<\/p>\n<p>As a <strong>conclusion<\/strong> we see that the <strong>sound quality is directly related with the memory consumption<\/strong>, so we might never get any high quality speech generated from Microcontrollers because we just don&#8217;t have enough memory available. I think there is a good reason why Google and Amazon are only providing their TTS functionality over the network.<\/p>\n<p>An <strong>alternative approach<\/strong> might be to record all required words, store them on a SD drive and just use these recordings to generate the sound output as demonstrated in my <a href=\"https:\/\/www.pschatzmann.ch\/home\/2022\/02\/16\/tts-with-prerecorded-audio-building-a-talking-clock\/\">arduino-simple-tts<\/a> project.<\/p>\n<p>I think the best option for <strong>dynamaically generated TTS<\/strong> is to delegate the &#8220;Speech Generation&#8221; (and maybe even the output) to a separate machine: A <strong>Raspberry Pi<\/strong> makes already all the difference and there are plenty of resources on the internet which cover this topic.<\/p>\n<p>My <strong>TTS projects of choice<\/strong> are<\/p>\n<ul>\n<li><a href=\"https:\/\/rhasspy.readthedocs.io\/en\/latest\/\">Rhasspy<\/a> which provides multiple different TTS implementations and a simple REST API.<\/li>\n<li><a href=\"https:\/\/github.com\/mozilla\/TTS\">Mozilla TTS<\/a> which implements some state of the art models<\/li>\n<\/ul>\n<p>Sending a Post request to the Rhasspy URL &#8220;http:\/\/address:12101\/api\/text-to-speech&#8221; is returning a WAV file: Here is the corresponding <strong>Arduino sketch<\/strong> which will send the <strong>request to Rhasspy and provides the output to I2S<\/strong>:<\/p>\n<pre><code>#include \"AudioTools.h\"\n#include \"AudioCodecs\/CodecWAV.h\"\n\nusing namespace audio_tools;  \n\n\/\/ UrlStream -copy-&gt; AudioOutputStream -&gt; WAVDecoder -&gt; I2S\nURLStream url(\"ssid\",\"password\");\nI2SStream i2s;                  \/\/ I2S stream \nWAVDecoder decoder;        \/\/ decode wav to pcm and send it to I2S\nEncodedAudioStream out(&amp;i2s, &amp;decoder); \/\/ output to decoder\nStreamCopy copier(out, url);    \/\/ copy in to out\n\n\nvoid setup() {\n  Serial.begin(115200);\n  AudioLogger::instance().begin(Serial, AudioLogger::Debug);  \n\n\/\/ setup i2s output\n  auto config = i2s.defaultConfig(TX_MODE);\n  config.sample_rate = 16000; \n  config.bits_per_sample = 16;\n  config.channels = 1;\n  i2s.begin(config);\n\n\/\/ rhasspy\n   url.begin(\"http:\/\/192.168.1.37:12101\/api\/text-to-speech?play=false\",  \"text\/plain\",POST,\"Hallo, my name is Alice\");\n}\n\nvoid loop(){\n  \/\/ copy audio from url -&gt; i2s\n  if (!copier.copy()) {\n    i2s.end();\n    LOGI(\"stopped\");\n    stop();\n  }\n}\n\n<\/code><\/pre>\n<p>This sketch (which is part of the <a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\">arduino-audio-tools<\/a> library) is also available on <a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\/tree\/main\/examples\/examples-tts\">github<\/a>.<\/p>\n<p>If your microcontroller does not support I2S you can use the following output classes instead:<\/p>\n<ul>\n<li>AnalogAudioStream<\/li>\n<li>PWMAudioOutput<\/li>\n<li>VS1053Stream<\/li>\n<\/ul>\n<p><strong>Addendum<\/strong><\/p>\n<p>A lot has happend since I wrote this library. The generic TTS Arduino library with the best audio quality by far is my <a href=\"https:\/\/www.pschatzmann.ch\/home\/2022\/11\/10\/espeak-ng-the-difficult-journey-to-an-arduino-library\/\">arduino-espeak-ng<\/a>.<\/p>\n<p>Here is the updated list of <a href=\"https:\/\/www.pschatzmann.ch\/home\/category\/text-to-speech\/\">all my tts blogs<\/a> that cover the topic TTS on micro controllers.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In my last couple of Blogs I was comparing the following Text To Speach (TTS) libraries which are available on Arduino: SAM Software Automatic Mouth TTS Text-to-Speech Library for Arduino Flite Festival lite I was hoping to find some TinyML based implementations, but so far without success: I put this [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_crdt_document":"","_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"footnotes":""},"categories":[20,22,35],"tags":[27],"class_list":["post-3229","post","type-post","status-publish","format-standard","hentry","category-arduino","category-machine-sound","category-text-to-speech","tag-tts"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Text To Speach in Arduino - Final Conclusions - Phil Schatzmann<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Text To Speach in Arduino - Final Conclusions - Phil Schatzmann\" \/>\n<meta property=\"og:description\" content=\"In my last couple of Blogs I was comparing the following Text To Speach (TTS) libraries which are available on Arduino: SAM Software Automatic Mouth TTS Text-to-Speech Library for Arduino Flite Festival lite I was hoping to find some TinyML based implementations, but so far without success: I put this [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/\" \/>\n<meta property=\"og:site_name\" content=\"Phil Schatzmann\" \/>\n<meta property=\"article:published_time\" content=\"2021-06-23T11:23:36+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-07-25T09:01:18+00:00\" \/>\n<meta name=\"author\" content=\"pschatzmann\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"pschatzmann\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/\"},\"author\":{\"name\":\"pschatzmann\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"headline\":\"Text To Speach in Arduino &#8211; Final Conclusions\",\"datePublished\":\"2021-06-23T11:23:36+00:00\",\"dateModified\":\"2024-07-25T09:01:18+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/\"},\"wordCount\":344,\"commentCount\":4,\"publisher\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"keywords\":[\"TTS\"],\"articleSection\":[\"Arduino\",\"Machine Sound\",\"Text To Speech\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/\",\"name\":\"Text To Speach in Arduino - Final Conclusions - Phil Schatzmann\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#website\"},\"datePublished\":\"2021-06-23T11:23:36+00:00\",\"dateModified\":\"2024-07-25T09:01:18+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2021\\\/06\\\/23\\\/text-to-speach-in-arduino-conclusions\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Text To Speach in Arduino &#8211; Final Conclusions\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#website\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/\",\"name\":\"Phil Schatzmann Consulting\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\",\"name\":\"pschatzmann\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\",\"contentUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\",\"width\":305,\"height\":305,\"caption\":\"pschatzmann\"},\"logo\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Text To Speach in Arduino - Final Conclusions - Phil Schatzmann","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/","og_locale":"en_US","og_type":"article","og_title":"Text To Speach in Arduino - Final Conclusions - Phil Schatzmann","og_description":"In my last couple of Blogs I was comparing the following Text To Speach (TTS) libraries which are available on Arduino: SAM Software Automatic Mouth TTS Text-to-Speech Library for Arduino Flite Festival lite I was hoping to find some TinyML based implementations, but so far without success: I put this [&hellip;]","og_url":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/","og_site_name":"Phil Schatzmann","article_published_time":"2021-06-23T11:23:36+00:00","article_modified_time":"2024-07-25T09:01:18+00:00","author":"pschatzmann","twitter_card":"summary_large_image","twitter_misc":{"Written by":"pschatzmann","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/#article","isPartOf":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/"},"author":{"name":"pschatzmann","@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"headline":"Text To Speach in Arduino &#8211; Final Conclusions","datePublished":"2021-06-23T11:23:36+00:00","dateModified":"2024-07-25T09:01:18+00:00","mainEntityOfPage":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/"},"wordCount":344,"commentCount":4,"publisher":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"keywords":["TTS"],"articleSection":["Arduino","Machine Sound","Text To Speech"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/","url":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/","name":"Text To Speach in Arduino - Final Conclusions - Phil Schatzmann","isPartOf":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#website"},"datePublished":"2021-06-23T11:23:36+00:00","dateModified":"2024-07-25T09:01:18+00:00","breadcrumb":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.pschatzmann.ch\/home\/2021\/06\/23\/text-to-speach-in-arduino-conclusions\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pschatzmann.ch\/home\/"},{"@type":"ListItem","position":2,"name":"Text To Speach in Arduino &#8211; Final Conclusions"}]},{"@type":"WebSite","@id":"https:\/\/www.pschatzmann.ch\/home\/#website","url":"https:\/\/www.pschatzmann.ch\/home\/","name":"Phil Schatzmann Consulting","description":"","publisher":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.pschatzmann.ch\/home\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1","name":"pschatzmann","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png","url":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png","contentUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png","width":305,"height":305,"caption":"pschatzmann"},"logo":{"@id":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png"}}]}},"post_mailing_queue_ids":[],"_links":{"self":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/3229","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/comments?post=3229"}],"version-history":[{"count":64,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/3229\/revisions"}],"predecessor-version":[{"id":6291,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/3229\/revisions\/6291"}],"wp:attachment":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/media?parent=3229"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/categories?post=3229"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/tags?post=3229"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}