Pendrokar

I've added, AFAIK, the only Lojban fine-tuned Text-To-Speech voice model to the HF Space. It was an experiment that I thought would fail badly, but somewhat succeeded. You can find it expanding the list of voices: huggingface.co/spaces/Pendrok… #lojban

@WhiteHouse Monster!

🚨 “If Iran doesn’t FULLY OPEN, WITHOUT THREAT, the Strait of Hormuz, within 48 HOURS from this exact point in time, the United States of America will hit and obliterate their various POWER PLANTS, STARTING WITH THE BIGGEST ONE FIRST…” - President DONALD J. TRUMP

@Fried_Cola The trigger system of Starcraft and Warcraft III is what made all of this possible

It’s crazy how much modern gaming owes to WC3 maps. MOBA, Auto Chess, DBD... the DNA is everywhere. I actually wanted to turn Jurassic Park Survival into a standalone game when I started my dev journey. Anyone remember this one? #gamedev #Warcraft3 #indiegame

@AmbJohnBolton The neocons are now arguing that real neoconservativism has never been tried

@Hytale Finally the words within magical spells will have a meaning behind them. "You have come too late... my work has already met... a Success." -MoM Merlin Still work to do though. #Hytale #HytaleModding x.com/i/status/20190…

There’s one more category to cover for the Hytale New Worlds Modding Contest! ⚔️ EXPERIENCES ⚔️ Unleash your ingenuity and imagination to create a new way to play Hytale ✨ Adventure maps, minigames, hard modes, or deep systems (skill trees, progression, crafting reworks). This will be a fun way to let your creativity run wild! Utilize all of Hytale’s creative tooling and tech available to breathe life into these new experiences. We are so excited to see what everyone submits for this category! (Trust us - we will be watching 👀) Event details + resources in the replies 🧵 #Hytale #HytaleModding

@hume_ai Eh.. multi stage @Gradio API for this space for speech synthesis. Meaning it can't be added easily to the TTS Arena fork. 🤷‍♂️

Today we're releasing our first open source TTS model, TADA! TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency. This means: → Zero content hallucinations across 1,000+ test samples → 5x faster than similar-grade LLM-based TTS → Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems → Free transcript alongside audio with no added latency

@TheInsiderPaper We know who started it, we know it is the same people that burnt the sky x.com/Pendrokar/stat…

NEW: Apocalyptic scenes in Tehran as thick black smoke from oil depot strikes hides the sunrise

@LivinginTehran We know who started it, we know who burned the sky x.com/Pendrokar/stat…

📹 Longshot view of Tehran's sky this morning. The footage begins with a view of a burning oil depot in southern Tehran and ends with another burning oil depot in the city's northwest.

@Osinttechnical When they couldn't defeat the enemy, they took out the sun itself. Animatrix - End of the Second Renaissance

Tehran is covered in thick black clouds of smoke this morning after a series of Israeli airstrikes struck multiple oil depots and a refinery. Locals report that the morning rain was black and oily.

@MalcontentmentT @KanwalSibal Why? Is the US at war with Iran?

@KanwalSibal Where exactly in International Humanitarian Law does it state that a warship that does not have protected status as a floating hospital, that has no ammunition, is not a legitimate target? What Section, Article, and Paragraph?

The Iranian ship will not be where it was if we had not invited it to talk part in our Milan exercise. We were the hosts. I am told that as per protocol for this exercise ships cannot carry any ammunition. It was defenceless. The Iranian naval personnel had paraded before our president . The attack by the US submarine was premeditated as the US was aware of the Iranian ship’s presence in the exercise to which the US navy was invited but withdrew from participation at the last minute, presumably with this operation in mind. The US has ignored India’s sensitivities as the ship was in these waters because of India’s invitation. We are far from politically or militarily responsible for the US attack. Our“responsibility” is at a moral and human plane. A word of condolence by the Indian Navy ( after political clearance) at the loss of lives of those who were our invitees and saluted our president would be in order.

@defoemark Added to TTS Arena fork. Though used the New York accent voice. huggingface.co/spaces/Pendrok…

We just open-sourced KaniTTS2 — a 400M param text-to-speech model that runs in 3GB VRAM with voice cloning support. And we’re releasing the full pretrain code so you can train your own TTS from scratch for any language. huggingface.co/nineninesix/ka…, huggingface.co/nineninesix/ka… Apache 2.0

@StefanMolyneux Is "collective self defense" term that the states use an oxymoron?

@andimarafioti Depends on the HF space. Voice Design gets a random voice. CustomVoice is a fine tuned model

@Pendrokar Did a few rounds. I think you're using a non-english speaker for qwen, so the samples sound a bit off.

Introducing Faster Qwen3TTS! Realistic voice generation at 4x real time: - Same amazing voice quality from Qwen's model - Streaming support with <200 ms to first audio - 5x faster than the official implementation Just pip install faster-qwen3-tts Try the demo!

@Lv10noob @CyberRobooo Look the positions of the robots between camera switches. They often do not align. These are video cuts. This performance was not LIVE.

@CyberRobooo point is - they are reliable enough so they show them on live tv at prime time. a failure would be devastating. this is next-level confidence. you can be sure they trust them already with much more tasks

🤯Absolutely insane. Unitree's humanoid robot team's performance at the 2026 Spring Festival Gala The significance of the humanoid robot's performance lies in letting 1.4 billion Chinese people know where the future lies.

Impressive! Even for a video montage, as there was no LIVE event taking place.

@StefanMolyneux See the last column of that leaderboard. It has been 2 years and Kokoro has never had trouble with 11labs. No Cease & Desist, no nothing... 150 times cheaper! @elevenlabs can only exist if the state protects its IP.

@StefanMolyneux What about training on the output of an AI model? Example. ElevenLabs strictly point out that it is against their ToS to do so. Yet Kokoro Text to Speech model was trained on 11labs v2.5 output which led to an excellent narrator model at 150x the price!!! artificialanalysis.ai/text-to-speech…

The Truth About AI Part 1 Stefan Molyneux looks at the philosophical and moral sides of artificial intelligence, particularly where it crosses with copyright laws and its effects on society. He points out how AI draws from copyrighted materials without getting permission, which brings up issues around intellectual property. Molyneux draws a comparison between standard ways of learning and what AI can do as a customized tutor, noting its ability to deliver information suited to individual needs. He cautions that AI could lower the worth of conventional media and put authors' incomes at risk by turning their creations into commodities. Molyneux calls for an approach where AI firms get approval from the original creators, stressing the importance of acknowledging authors' work as AI becomes more common. Chapters: 0:00:00 Introduction to AI's Impact 0:00:15 The Ethics of Copyright 0:04:19 Transformative Uses of AI 0:07:55 The Role of AI in Learning 0:16:22 The Nature of AI's Existence 0:20:37 AI and Intellectual Property Issues 0:23:15 AI as a Government Program GET FREEDOMAIN MERCH! shop.freedomain.com SUBSCRIBE TO ME ON X! x.com/StefanMolyneux Follow me on Youtube! @freedomain1" target="_blank" rel="nofollow noopener">youtube.com/@freedomain1 GET MY NEW BOOK 'PEACEFUL PARENTING', THE INTERACTIVE PEACEFUL PARENTING AI, AND THE FULL AUDIOBOOK! peacefulparenting.com Join the PREMIUM philosophy community on the web for free! Subscribers get 12 HOURS on the "Truth About the French Revolution," multiple interactive multi-lingual philosophy AIs trained on thousands of hours of my material - as well as AIs for Real-Time Relationships, Bitcoin, Peaceful Parenting, and Call-In Shows! You also receive private livestreams, HUNDREDS of exclusive premium shows, early release podcasts, the 22 Part History of Philosophers series and much more! See you soon! freedomain.locals.com/support/promo/…

@StefanMolyneux We don't?

You don’t understand the basic argument

@StefanMolyneux Finely tuned?

Sure, I have a number of AI bots on my website, trained deeply on my philosophy

@flyarcher @LA28 @TeamUSA The music needs to be even louder to cancel out the noise of the VTOL

Where we're going, we don't need roads. Proud Supporter of @LA28 and @TeamUSA