An interactive demo for developers to try the new text-to-speech model in the #openai #tts #audio #api https://www.openai.fm

Now there's MLX-Audio! They have Kokoro and CSM-1B for now. It's the same dev team for MLX-VLM, so I have high hope! #TTS #AI #ML https://github.com/Blaizzy/mlx-audio

For everybody who uses the open source TTS (text-to-speech) application Piper: I have created a Docker file to run Piper directly within the container. No need to install the correct Python version. Everything comes pre-installed in the Docker image. Open source too: https://github.com/tderflinger/piper-cli-docker
#python #piper #tts #voice #docker #opensource

Demo of new Siri voices in VoiceOver on iOS 18.4.

A worker at the General Services Administration resigned in protest rather than giving Elon Musk ally Thomas Shedd access to Notify.gov, the system used to send mass text messages to the public, which they said would allow him to see "all personally identifiable information moving through the Notify system, including phone numbers.” @404media reports:
https://www.404media.co/musk-ally-demands-admin-access-to-system-that-lets-government-text-the-public/

ElevenLabs Reader on Android:
8 percent.. Progress: %1$s of %2$s. Slider

Well, that happened. I guess I should report that at some point.

@accessibleandroid #Android #ElevenLabs #AI #TTS #accessibility #TalkBack #blind

So, I finally hit the jackpot! Using the Tech Freedom TTS engine, set to use the eSpeak TTS engine, I have absolutely no lag where the TTS engine is concerned. Of course, TalkBack can still lag when swiping or scrolled, but I'm surprisingly getting used to that. So the issue I have with using Espeak by itself is that sometimes it'll switch dialects from US to UK English, and that is rather jarring to me. Also, I tried this other TTS engine on FDroid, which uses Piper voices, and it's far more responsive than the other one. That TTS engine is called SherpaTTS

Privacy? Data Protection? Respect for Civil Liberties? "404 Not Found" when it comes to scumbags who love scifi dystopias...

"Thomas Shedd, a Musk-associate and now head of the General Services Administration’s Technology Transformation Services (TTS), told government tech workers in a meeting this week that the administration plans to widely deploy AI throughout the government. Shedd also said the administration would need help altering login.gov, a government login system, to further integrate with sensitive systems like social security “to further identify individuals and detect and prevent fraud,” which employees identified on the meeting as “an illegal task.”

Shedd, who is a former Tesla engineer, said the government should “try to get consent,” regarding login.gov changes but that “we should still push forward and see what we can do.”

WIRED and the New York Times previously reported on aspects of the meeting. 404 Media has now obtained audio of the full meeting and quotes it extensively below. Shedd told TTS workers that the administration would need help making radical changes to various government systems: “Things are going to get intense,” he said."

https://www.404media.co/things-are-going-to-get-intense-how-a-musk-ally-plans-to-push-ai-on-the-government/

Finally there is a decent open source privacy respecting Text To Speech engine for Android. I've been using RHvoice, which is functional but robotic sounding - nicely Sherpa TTS is way better :)
https://github.com/woheller69/ttsEngine
#android #foss #apks #apps #texttospeech #tts #privacy #fdroid #opensource #degoogled

Are you always on the lookout for new text-to-speech software? Jarod's Journey has you covered with "My Top 5 Open Source TTS off in 2024"! This video is packed with great options that enhance #a11y. Plus, having a synthesized version of your voice can be a lifesaver if you ever lose your voice! Don’t miss it: https://youtu.be/lPitjhhodaw or Invidious: https://invidious.reallyaweso.me/watch?v=lPitjhhodaw #TextToSpeech #OpenSource #Accessibility #AssistiveTech #TTS #OpenSourceSoftware

For all you retro text to speech nerds out there, here's a recording of Superior Software's "Speech" for the Amstrad CPC computer (1986). This was a small piece of Z80 machine code that played phonemes through the computer's AY-3-8912 sound chip

It sounds pretty harsh, and there are a number of hard clicks in the output I couldn't easily fix.

I've included what I think is the spoken script as alt text

So, the AI Kokoro TTS has the Adam voice, which I think is near the best Eleven Labs has made. Funny that Kokoro is pretty well testing the whole idea of using model outputs for training. So I tried running a book about Linux through it, and shockingly, it seems to be able to pronounce some commands correctly, like ls, rmdir, and mkdir. Although now that I've tried them, ESpeak pronounces them well too. Now to try it with stuff like "press Alt + F, I, E" and stuff like that.

It sounds like Kokoro TTS cloned Sky voice from ChatGPT so you can run locally. It has slightly poor quality, but it's definitely Sky. Choose Sky and try on their demo. #ChatGPT #OpenAI #TTS #AI https://huggingface.co/spaces/hexgrad/Kokoro-TTS