Superman's banner
Superman's profile picture

Superman

@thesupermanmx • 12,027 subscribers

AI & Neuroscience

Shorts

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

104,663 просмотров

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

someone literally vibe-coded "twitch" for running 🤯 you stream your run live and people watch your dot move across a 3d map of the city in real time. → live 3d map tracking your exact route → pace, distance, heart rate updating live on screen → live graphs for elevation and heart rate → viewers chat with you mid-run and yell at you to push up the hill 100% free..
0:47
thesupermanmx's profile picture

someone literally vibe-coded "twitch" for running 🤯 you stream your run live and people watch your dot move across a 3d map of the city in real time. → live 3d map tracking your exact route → pace, distance, heart rate updating live on screen → live graphs for elevation and heart rate → viewers chat with you mid-run and yell at you to push up the hill 100% free..

Superman

1,618,556 просмотров • 1 месяц назад

ssomeone vibe-coded a video stream that is secretly 100% text so it can't be blocked. It’s called ASCIline. It renders streams 360p video at 30fps with zero video element on the page. every frame is colored text characters painted on a canvas. 100% Open Source.
0:34
thesupermanmx's profile picture

ssomeone vibe-coded a video stream that is secretly 100% text so it can't be blocked. It’s called ASCIline. It renders streams 360p video at 30fps with zero video element on the page. every frame is colored text characters painted on a canvas. 100% Open Source.

Superman

53,731 просмотров • 3 месяцев назад

Someone open-sourced a 66M parameter model that beats ElevenLabs, OpenAI, and Gemini and runs entirely offline on a Raspberry Pi. it's called Supertonic, a text-to-speech model so fast it turns an entire webpage into audio in under 1 second. locally. offline. for free. text-to-speech has lived in the cloud for years. every spoken character was an API call and a fraction of a cent. Supertonic 3 kills that entirely. the model is 99M parameters. ships as a single ONNX file. hits 167× faster than real-time on a laptop CPU. that's ~1,263 characters of speech per second. other open systems sit at 55–287. no cloud. no API. no GPU. → 31 languages, no separate adapters → works inside a browser tab (WebGPU/WASM) → handles phone numbers, currency, dates — no preprocessing → inline tags for laugh and breath → Turns an entire webpage into audio in under 1 second → 44.1kHz studio-grade WAV, no upsampler needed` and on real-world text, "$5.2M", "(212) 555-0142 ext. 402", "30kph”, it's the only one that reads them correctly. ElevenLabs Flash, OpenAI TTS-1, Gemini 2.5 Flash all fail. Supertonic passes. 11.2k stars. 100% Open Source.
1:00
thesupermanmx's profile picture

Someone open-sourced a 66M parameter model that beats ElevenLabs, OpenAI, and Gemini and runs entirely offline on a Raspberry Pi. it's called Supertonic, a text-to-speech model so fast it turns an entire webpage into audio in under 1 second. locally. offline. for free. text-to-speech has lived in the cloud for years. every spoken character was an API call and a fraction of a cent. Supertonic 3 kills that entirely. the model is 99M parameters. ships as a single ONNX file. hits 167× faster than real-time on a laptop CPU. that's ~1,263 characters of speech per second. other open systems sit at 55–287. no cloud. no API. no GPU. → 31 languages, no separate adapters → works inside a browser tab (WebGPU/WASM) → handles phone numbers, currency, dates — no preprocessing → inline tags for laugh and breath → Turns an entire webpage into audio in under 1 second → 44.1kHz studio-grade WAV, no upsampler needed` and on real-world text, "$5.2M", "(212) 555-0142 ext. 402", "30kph”, it's the only one that reads them correctly. ElevenLabs Flash, OpenAI TTS-1, Gemini 2.5 Flash all fail. Supertonic passes. 11.2k stars. 100% Open Source.

Superman

30,416 просмотров • 3 месяцев назад

Больше нет контента для загрузки