det.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mastodon Server des Unterhaltungsfernsehen Ehrenfeld zum dezentralen Diskurs.

Administered by:

Server stats:

1.8K
active users

#tts

3 posts3 participants0 posts today
Verfassungklage@troet.cafe<p><a href="https://troet.cafe/tags/LibreOffice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LibreOffice</span></a> <a href="https://troet.cafe/tags/Texte" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Texte</span></a> unter <a href="https://troet.cafe/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> <a href="https://troet.cafe/tags/diktieren" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>diktieren</span></a> mit <a href="https://troet.cafe/tags/SpeechNote" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechNote</span></a>:</p><p>Die <a href="https://troet.cafe/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> und <a href="https://troet.cafe/tags/STT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STT</span></a> Anwendung <a href="https://troet.cafe/tags/Speech_Note" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Speech_Note</span></a> liefert gute Ergebnisse, auch auf mittelstarker Hardware. Die verschiedenen <a href="https://troet.cafe/tags/KI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KI</span></a>- Modelle werden alle lokal ausgeführt. </p><p>Speech Note als <a href="https://troet.cafe/tags/Flatpak" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Flatpak</span></a> installiert. Nach der Installation belegt das Programm knapp 4 GB auf der SSD. Wer knappen Massenspeicher hat, sollte sich dessen bewusst sein. Doch damit nicht genug; beim ersten Starten der Anwendung darf man eine Sprache...</p><p><a href="https://gnulinux.ch/libre-office-texte-unter-linux-diktieren-mit-speech-note" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">gnulinux.ch/libre-office-texte</span><span class="invisible">-unter-linux-diktieren-mit-speech-note</span></a></p>
Johannes Oschlies <a href="https://social.anoxinon.de/@gnulinux" rel="nofollow noopener" target="_blank"></a>&nbsp;<span><a href="https://social.anoxinon.de/@gnulinux" rel="nofollow noopener" target="_blank">GNU/Linux.ch</a> schrieb den folgenden <a href="https://social.anoxinon.de/@gnulinux/115031495258496713" rel="nofollow noopener" target="_blank">Beitrag</a> <span class="">Fri, 15 Aug 2025 09:02:01 +0200</span></span> Libre Office Texte unter Linux diktieren mit Speech Note<br><br>Die TTS und STT Anwendung Speech Note liefert gute Ergebnisse, auch auf mittelstarker Hardware. Die verschiedenen KI-Modelle werden alle lokal ausgeführt. <br><br><a href="https://social.anoxinon.de/tags/TTS" rel="nofollow noopener" target="_blank">#TTS</a> <a href="https://social.anoxinon.de/tags/STT" rel="nofollow noopener" target="_blank">#STT</a> <a href="https://social.anoxinon.de/tags/Texte_sprechen" rel="nofollow noopener" target="_blank">#Texte_sprechen</a> <a href="https://social.anoxinon.de/tags/LibreOffice" rel="nofollow noopener" target="_blank">#LibreOffice</a> <a href="https://social.anoxinon.de/tags/Speech" rel="nofollow noopener" target="_blank">#Speech</a> <a href="https://social.anoxinon.de/tags/Linux" rel="nofollow noopener" target="_blank">#Linux</a><br><br><a href="https://gnulinux.ch/libre-office-texte-unter-linux-diktieren-mit-speech-note" rel="nofollow noopener" target="_blank">https://gnulinux.ch/libre-office-texte-unter-linux-diktieren-mit-speech-note</a><br>
GNU/Linux.ch<p>Libre Office Texte unter Linux diktieren mit Speech Note</p><p>Die TTS und STT Anwendung Speech Note liefert gute Ergebnisse, auch auf mittelstarker Hardware. Die verschiedenen KI-Modelle werden alle lokal ausgeführt. </p><p><a href="https://social.anoxinon.de/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> <a href="https://social.anoxinon.de/tags/STT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STT</span></a> <a href="https://social.anoxinon.de/tags/Texte_sprechen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Texte_sprechen</span></a> <a href="https://social.anoxinon.de/tags/LibreOffice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LibreOffice</span></a> <a href="https://social.anoxinon.de/tags/Speech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Speech</span></a> <a href="https://social.anoxinon.de/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a></p><p><a href="https://gnulinux.ch/libre-office-texte-unter-linux-diktieren-mit-speech-note" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">gnulinux.ch/libre-office-texte</span><span class="invisible">-unter-linux-diktieren-mit-speech-note</span></a></p>
Boiling Steam<p>Abogen – Generate audiobooks from EPUBs, PDFs and text: <a href="https://github.com/denizsafak/abogen" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">github.com/denizsafak/abogen</span><span class="invisible"></span></a> <br><a href="https://mastodon.cloud/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linux</span></a> <a href="https://mastodon.cloud/tags/update" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>update</span></a> <a href="https://mastodon.cloud/tags/release" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>release</span></a> <a href="https://mastodon.cloud/tags/foss" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>foss</span></a> <a href="https://mastodon.cloud/tags/abogen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>abogen</span></a> <a href="https://mastodon.cloud/tags/epub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epub</span></a> <a href="https://mastodon.cloud/tags/pdf" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pdf</span></a> <a href="https://mastodon.cloud/tags/audiobook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>audiobook</span></a> <a href="https://mastodon.cloud/tags/generation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generation</span></a> <a href="https://mastodon.cloud/tags/tts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tts</span></a></p>
IT News<p>Numbers Station Simulator, Right In Your Browser - Do you find an odd comfort in the uncanny, regular intonations of a Numbers Statio... - <a href="https://hackaday.com/2025/07/29/numbers-station-simulator-right-in-your-browser/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2025/07/29/number</span><span class="invisible">s-station-simulator-right-in-your-browser/</span></a> <a href="https://schleuss.online/tags/numbersstation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>numbersstation</span></a> <a href="https://schleuss.online/tags/softwarehacks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>softwarehacks</span></a> <a href="https://schleuss.online/tags/webspeechapi" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>webspeechapi</span></a> <a href="https://schleuss.online/tags/art" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>art</span></a> <a href="https://schleuss.online/tags/tts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tts</span></a></p>
voxelNon-blind user wondering about TTS accessibility problems
Dan Gero<p>I wrote this blueprint for a web app that would make it easier for people to build voices and languages for different TTS engines. It's vague, but it's a start if anyone wants to contribute to it or eventually create the real thing. Boosts appreciated, as always. <a href="https://github.com/lower-elements/Voice-Creator-Studio" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/lower-elements/Voic</span><span class="invisible">e-Creator-Studio</span></a> <a href="https://vocalounge.cafe/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> <a href="https://vocalounge.cafe/tags/Accessibility" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Accessibility</span></a> <a href="https://vocalounge.cafe/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://vocalounge.cafe/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ML</span></a></p>
Terence Eden’s Blog<p><strong>Synthetic Poetry</strong></p><p><a href="https://shkspr.mobi/blog/2021/07/synthetic-poetry/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">shkspr.mobi/blog/2021/07/synth</span><span class="invisible">etic-poetry/</span></a></p><p></p><p>I've been experimenting with <a href="https://aws.amazon.com/polly/" rel="nofollow noopener" target="_blank">Amazon's Polly service</a>. It's their fancy text-to-sort-of-human-style-speech system. Think "Alexa" but with a variety of voices, genders, and accents.</p><p>Here's "Brian" - their English, male, received pronunciation voice - reading John Betjeman's poem "<a href="https://en.wikipedia.org/wiki/Slough_(poem)" rel="nofollow noopener" target="_blank">Slough</a>":</p><p></p> <a href="https://shkspr.mobi/blog/wp-content/uploads/2021/07/slough.mp4" rel="nofollow noopener" target="_blank">https://shkspr.mobi/blog/wp-content/uploads/2021/07/slough.mp4</a> <p></p><p>The pronunciation of all the words is incredibly lifelike. If you heard it on the radio, it might sound like a half-familiar BBC presenter. It has a calm, even tone which suits the poem splendidly.</p><p>The rhythm is also spot on. That's mostly a function of the short lines and helpful punctuation the poem contains. Much like iambic pentameter, or a limerick, the syllables lend themselves to a specific and identifiable cadence.</p><p>But the emphasis is all wrong. The poem just... ends. There's no sense of finality in the tone. You'd expect a competent reader to recognise "tinned <em>minds</em>" as being worthy of stressing. Polly does have some capability to mark specific words for emphasis, but it's all very manual.</p><p>There's no synthetic emotion. Do you feel the rage, desperation, sadness, hopelessness of the poem? While <a href="https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html" rel="nofollow noopener" target="_blank">Polly has some SSML (Speech Synthesis Markup Language) support</a> - the range of emotions it can express are <a href="https://developer.amazon.com/en-US/docs/alexa/custom-skills/speech-synthesis-markup-language-ssml-reference.html#amazon-emotion" rel="nofollow noopener" target="_blank">severely limited</a>. And, again, must be applied manually.</p><p><strong>"I used to be an adventurer like you, but then i took an arrow in the knee!"</strong></p><p>One of the reasons <a href="https://knowyourmeme.com/memes/i-took-an-arrow-in-the-knee" rel="nofollow noopener" target="_blank">stock phrases</a> pop up so often in video games is that it is expensive to write and record thousands of different lines of dialogue.</p><p>We're <em>almost</em> at a stage where a computer can procedurally generate lines for background characters to speak, and then "record" an audio version in an array of styles. No more expensive voice actors, no more memetic references for in-group homophily. Each player of a game will have a completely different dialogue experience.</p><p>But the bit that we're <em>still</em> missing is the automation of emphasis and emotion and comic timing and understatement and... all the things which trained actors spend years learning how to do successfully.</p><p>In 2011, the film critic Roger Ebert had surgery which eliminated his voice. He proposed the following <a href="https://bits.blogs.nytimes.com/2011/03/07/roger-ebert-tests-his-vocal-cords-and-comedic-delivery/?src=me&amp;_r=0" rel="nofollow noopener" target="_blank">"Ebert Test"</a> for synthetic voices:</p><blockquote><p>If the computer can successfully tell a joke, and do the timing and delivery, as well as <a href="https://www.youtube.com/watch?v=y-LD9Xgqf6w" rel="nofollow noopener" target="_blank">Henny Youngman</a>, then that’s the voice I want.</p></blockquote><p>We're <em>so</em> close, I can taste it. The Turing Test for realistic voices is whether they can move the audience to tears with poetry.</p><p></p><p><a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/ai/" target="_blank">#AI</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/amazon/" target="_blank">#Amazon</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/tts/" target="_blank">#tts</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/turing/" target="_blank">#turing</a></p>
Terence Eden’s Blog<p><strong>1KB JS Numbers Station</strong></p><p><a href="https://shkspr.mobi/blog/2025/07/1kb-js-numbers-station/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">shkspr.mobi/blog/2025/07/1kb-j</span><span class="invisible">s-numbers-station/</span></a></p><p></p><p>Code Golf is the art/science of creating wonderful little demos in an artificially constrained environment. This year the <a href="https://js1024.fun/" rel="nofollow noopener" target="_blank">js1024 competition</a> was looking for entries with the theme of "Creepy".</p><p>I am not a serious bit-twiddler. I can't create JS shaders which produce intricate 3D worlds in a scrap of code. But I <em>can</em> use slightly obscure JavaScript APIs!</p><p>There's something deliciously creepy about <a href="https://priyom.org/number-stations" rel="nofollow noopener" target="_blank">Numbers Stations</a> - the weird radio frequencies which broadcast seemingly random numbers and words. Are they spies communicating? Commands for nuclear missiles? Long range radio propagation tests? Who knows!</p><p>So I decided to build one. <a href="https://js1024.fun/demos/2025/24/bar" rel="nofollow noopener" target="_blank">Play with the demo</a>.</p><p>Obviously, even the <a href="https://shkspr.mobi/blog/2020/09/a-floppy-disk-mp3-player-using-a-raspberry-pi/" rel="nofollow noopener" target="_blank">most extreme opus compression</a> can't fit much audio into 1KB. Luckily, JavaScript has you covered! Most modern browsers have a built-in Text-To-Speech (TTS) API.</p><p>Here's the most basic example:</p><pre><code>m = new SpeechSynthesisUtterance;m.text = "Hello";speechSynthesis.speak(m);</code></pre><p>Run that JS and your computer will speak to you!</p><p>In order to make it creepy, I played about with the rate (how fast or slow it speaks) and the pitch (how high or low).</p><pre><code>m.rate=Math.random();m.pitch=Math.random()*2;</code></pre><p>It worked disturbingly well! High pitched drawls, rumbling gabbling, the languid cadence of a chattering friend. All rather creepy.</p><p>But <em>what</em> could I make it say? Getting it to read out numbers is pretty easy - this will generate a random integer:</p><pre><code>s = Math.ceil( Math.random()*1000 );</code></pre><p>But a list of words would be tricky. There's not much space in 1,024 bytes for anything complex. The rules say I can't use any external resources; so are there any <em>internal</em> sources of words? Yes!</p><pre><code>Object.getOwnPropertyNames( globalThis );</code></pre><p>That gets all the properties of the global object which are available to the browser! Depending on your browser, that's over 1,000 words!</p><p>But there's a slight problem. Many of them are quite "computery" words like "ReferenceError", "URIError", "Float16Array". I wanted all the <em>single</em> words - that is, anything which only has one capital letter and that's at the start.</p><pre><code>const l = (n) =&gt; { return ((n.match(/[A-Z]/g) || []).length === 1 &amp;&amp; (n.charAt(0).match(/[A-Z]/g) || []).length === 1);};// Get a random result from the filters = Object.getOwnPropertyNames( globalThis ).filter( l ).sort( ()=&gt;.5-Math.random() )[0]</code></pre><p>Rather pleasingly, that brings back creepy words like "Event", "Atomics", and "Geolocation".</p><p>Of course, Numbers Stations don't just broadcast in English. The TTS system can vocalise in multiple languages.</p><pre><code>// Set the language to Russianm.lang = "ru-RU";</code></pre><p>OK, but where do we get all those language strings from? Again, they're built in and can be retrieved randomly.</p><pre><code>var e = window.speechSynthesis.getVoices();m.lang = e[ (Math.random()*e.length) |0 ]</code></pre><p>If you pass the TTS the number 555 and ask it to speak German, it will read out <i>fünfhundertfünfundfünfzig</i>.</p><p>And, if you tell the TTS to speak an English word like "Worker" in a foreign language, it will pronounce it with an accent.</p><p>Randomly altering the pitch, speed, and voice to read out numbers and dissociated words produces, I think, a rather creepy effect.</p><p>If you want to test it out, you can press this button. I find that it works best in browsers with a good TTS engine - let me know how it sounds on your machine.</p><p>🅝🅤🅜🅑🅔🅡🅢 🅢🅣🅐🅣🅘🅞🅝</p><p>With the remaining few bytes at my disposal, I produced a quick-and-dirty random pattern using Unicode drawing blocks. It isn't very sophisticated, but it does have a little random animation to it.</p><p>You can <a href="https://js1024.fun/demos/2025" rel="nofollow noopener" target="_blank">play with all the js1024 entries</a> - I would be delighted if you voted <a href="https://js1024.fun/demos/2025/24/bar" rel="nofollow noopener" target="_blank">for mine</a>.</p><p></p><p><a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/code/" target="_blank">#code</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/html/" target="_blank">#HTML</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/javascript/" target="_blank">#javascript</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://shkspr.mobi/blog/tag/tts/" target="_blank">#tts</a></p>
Terence Eden<p>🆕 blog! “1KB JS Numbers Station”</p><p>Code Golf is the art/science of creating wonderful little demos in an artificially constrained environment. This year the js1024 competition was looking for entries with the theme of "Creepy".</p><p>I am not a serious bit-twiddler. I can't create JS shaders which produce intricate 3D worlds in a scrap of code. But I can use slightly obscure JavaScript…</p><p>👀 Read more: <a href="https://shkspr.mobi/blog/2025/07/1kb-js-numbers-station/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">shkspr.mobi/blog/2025/07/1kb-j</span><span class="invisible">s-numbers-station/</span></a><br>⸻<br><a href="https://mastodon.social/tags/code" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>code</span></a> <a href="https://mastodon.social/tags/HTML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HTML</span></a> <a href="https://mastodon.social/tags/javascript" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>javascript</span></a> <a href="https://mastodon.social/tags/tts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tts</span></a></p>
Andre Louis<p>Here's a quick demo on how to enable TTS on the Nintendo Switch 2 from the home screen. Hopefully these menus are the same across all devices, though I have no way to know that for certain.</p><p>Edit: For other blind Switch/Switch 2 owners, I started a WhatsApp group to discuss the accessibility of the console and it's games. DM if you'd like to join.</p><p>Download: <a href="https://onj.me/media/Switch2_Accessibility.mp3" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">onj.me/media/Switch2_Accessibi</span><span class="invisible">lity.mp3</span></a><br><a href="https://universeodon.com/tags/Nintendo" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Nintendo</span></a> <a href="https://universeodon.com/tags/Switch2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Switch2</span></a> <a href="https://universeodon.com/tags/Accessibility" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Accessibility</span></a> <a href="https://universeodon.com/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> <a href="https://universeodon.com/tags/ScreenReader" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ScreenReader</span></a></p>
Devin Prater :blind:<p>Awww, the Alexa feature where it would read aloud Kindle books isn't available for Alexa Plus. Ah well, I'm just glad Kindle works much better on Android now.<br><a href="https://tweesecake.social/tags/accessibility" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>accessibility</span></a> <a href="https://tweesecake.social/tags/kindle" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>kindle</span></a> <a href="https://tweesecake.social/tags/amazon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>amazon</span></a> <a href="https://tweesecake.social/tags/alexa" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>alexa</span></a> <a href="https://tweesecake.social/tags/AlexaPlus" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlexaPlus</span></a> <a href="https://tweesecake.social/tags/blind" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>blind</span></a> <a href="https://tweesecake.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a></p>
Debby<p><span class="h-card" translate="no"><a href="https://mastodon.social/@thelinuxEXP" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>thelinuxEXP</span></a></span> I really like Speech Note! It's a fantastic tool for quick and local voice transcription in multiple languages, created by <span class="h-card" translate="no"><a href="https://mastodon.social/@mkiol" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>mkiol</span></a></span> </p><p>It's incredibly handy for capturing thoughts on the go, conducting interviews, or making voice memos without worrying about language barriers. The app uses strictly locally running LLMs, and its ease of use makes it a standout choice for anyone needing offline transcription services.</p><p>I primarily use <a href="https://hear-me.social/tags/WhisperAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WhisperAI</span></a> for transcription and Piper for voice, but many other models are available as well. </p><p>It is available as flatpak and <a href="https://github.com/mkiol/dsnote" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/mkiol/dsnote</span><span class="invisible"></span></a> </p><p><a href="https://hear-me.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> <a href="https://hear-me.social/tags/transcription" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>transcription</span></a> <a href="https://hear-me.social/tags/TextToSpeech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TextToSpeech</span></a> <a href="https://hear-me.social/tags/translator" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>translator</span></a> translation <a href="https://hear-me.social/tags/offline" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>offline</span></a> <a href="https://hear-me.social/tags/machinetranslation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinetranslation</span></a> <a href="https://hear-me.social/tags/sailfishos" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sailfishos</span></a> <a href="https://hear-me.social/tags/SpeechSynthesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechSynthesis</span></a> <a href="https://hear-me.social/tags/SpeechRecognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechRecognition</span></a> <a href="https://hear-me.social/tags/speechtotext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechtotext</span></a> <a href="https://hear-me.social/tags/nmt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nmt</span></a> <a href="https://hear-me.social/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linux</span></a>-desktop <a href="https://hear-me.social/tags/stt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stt</span></a> <a href="https://hear-me.social/tags/asr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>asr</span></a> <a href="https://hear-me.social/tags/flatpak" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>flatpak</span></a>-applications <a href="https://hear-me.social/tags/SpeechNote" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechNote</span></a></p>
digituba<p>SAM Software Automatic Mouth<br><a href="https://discordier.github.io/sam/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">discordier.github.io/sam/</span><span class="invisible"></span></a><br>This is a vanilla Javascript port of the Text-To-Speech (TTS) software SAM (Software Automatic Mouth) for the Commodore C64 published in the year 1982 by Don't Ask Software (now SoftVoice, Inc.).</p><p>It works in your web browser in the link above 🤖<br><a href="https://mastodon.social/tags/RetroGaming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RetroGaming</span></a> <a href="https://mastodon.social/tags/Commodore" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Commodore</span></a> <a href="https://mastodon.social/tags/C64" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>C64</span></a> <a href="https://mastodon.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a></p>
LinuxNews.de<p>Mozilla Common Voice Corpus 22.0 veröffentlicht<br><a href="https://linuxnews.de/mozilla-common-voice-corpus-22-0-veroeffentlicht/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">linuxnews.de/mozilla-common-vo</span><span class="invisible">ice-corpus-22-0-veroeffentlicht/</span></a> <a href="https://social.anoxinon.de/tags/mozilla" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mozilla</span></a> <a href="https://social.anoxinon.de/tags/tts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tts</span></a> <a href="https://social.anoxinon.de/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a></p>
Kevin Karhan :verified:<p><span class="h-card" translate="no"><a href="https://goo.dgirl.gay/@purplerabbit" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>purplerabbit</span></a></span> <span class="h-card" translate="no"><a href="https://nileane.fr/@nileane" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>nileane</span></a></span> yeah, this really pisses me off too.</p><p><a href="https://infosec.space/tags/YouTube" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>YouTube</span></a> deciding to <a href="https://infosec.space/tags/AutoDub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AutoDub</span></a> shit for no valid reason is only.worsened by the fact that they have the most horrendous <a href="https://infosec.space/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> voices one can imagine.</p><ul><li>Not even the funny <em>"We are Anonymous!"</em> kinda style but the most shitty output ever!</li></ul>
moagee<p>völlig underrated:</p><p><a href="https://chaos.social/tags/SpeechNote" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechNote</span></a> ist eine datenschutzfreundliche Linux-App, die Sprache in Text umwandelt (<a href="https://chaos.social/tags/STT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STT</span></a>), Text vorliest (auch Dateien) (<a href="https://chaos.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a>) und übersetzt – alles lokal ohne Internetverbindung.<br>Viele Sprachen und Open-Source-Modelle stehen zum einbinden zur Verfügung!</p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/GitHub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHub</span></a> is Leaking Trump’s Plans to 'Accelerate' <a href="https://hachyderm.io/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> Across <a href="https://hachyderm.io/tags/US" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>US</span></a> <a href="https://hachyderm.io/tags/Government" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Government</span></a><br>The <a href="https://hachyderm.io/tags/AIgov" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIgov</span></a> repository and staging site vanished when asked questions, but don't worry – they captured backups.<br>AI gov will serve as a hub for government agencies to begin adding AI to their operations, as was envisioned by <a href="https://hachyderm.io/tags/GSA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GSA</span></a> <a href="https://hachyderm.io/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> chief and <a href="https://hachyderm.io/tags/ElonMusk" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ElonMusk</span></a> ally <a href="https://hachyderm.io/tags/ThomasShedd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ThomasShedd</span></a> when he took control of the team in late January. <br><a href="https://www.404media.co/github-is-leaking-trumps-plans-to-accelerate-ai-across-government/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">404media.co/github-is-leaking-</span><span class="invisible">trumps-plans-to-accelerate-ai-across-government/</span></a></p>
Hacker News<p>Open source TTS by Resemble (claiming they are sota)</p><p><a href="https://github.com/resemble-ai/chatterbox" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/resemble-ai/chatter</span><span class="invisible">box</span></a></p><p><a href="https://mastodon.social/tags/HackerNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HackerNews</span></a> <a href="https://mastodon.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://mastodon.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> <a href="https://mastodon.social/tags/Resemble" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Resemble</span></a> <a href="https://mastodon.social/tags/SOTA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SOTA</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/Technology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Technology</span></a> <a href="https://mastodon.social/tags/GitHub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHub</span></a></p>
𝖧𝖾𝗂𝗄𝗈 𝗩𝗼𝗴𝗲𝗹𝗴𝗲𝘀𝗮𝗻𝗴 𝖡𝖾𝗋𝗅𝗂𝗇<p>Open source <a href="https://mastodon.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> model that outperforms ElevenLabs. 5 seconds of own voice are enough for okay-ish results. Just tested it with my voice. Impressive. <a href="https://github.com/resemble-ai/chatterbox" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/resemble-ai/chatter</span><span class="invisible">box</span></a></p>