We just released QVAC TranscribePsy, a speech-to-text model small enough to run inside a phone app.
It covers 25 European languages on a laptop and 8 on a phone, and on an iPhone 17 Pro Max's Neural Engine the 8-language build transcribes a 10-minute recording in 1.65 seconds.
Glasses, robots and phones are moving to voice, and each of them first has to write down what you said. Today that step mostly happens on a server.
TranscribePsy does it on the phone or laptop, so dictation and meeting notes keep working with no signal, and a private conversation can be transcribed without the recording ever leaving the room.
Run it on our qvac-fabric-speech.cpp's parakeet engine, which optimizes for efficient execution and delivers the highest performance.
Get the models: https://t.co/DERAKXa23D
QVAC's mission is to make intelligence a universal right, not a subscription. Our AI runs on your phone or laptop, and it is open source so you can verify it.
@paoloardoino expects 70% of everyday AI tasks to run locally in three years.
The Math of You ๐
A music video made end-to-end with Opus 5.5. Song by HN on Suno.
Storyboard, characters, animation, edit: all done by a Claude Code skill I built. It's free and open source on my GitHub (macOS).
Have Fun Staying Poor. A love letter to every altcoin, from a Bitcoin quasi-maximalist. Lyrics by Grok, song by Suno, Opus 5.5 for the video end-to-end.
Have Fun Staying Poor. A love letter to every altcoin, from a Bitcoin quasi-maximalist. Lyrics by Grok, song by Suno, Opus 5.5 for the video end-to-end.
Have Fun Staying Poor. A love letter to every altcoin, from a Bitcoin quasi-maximalist. Lyrics by Grok, song by Suno, Opus 5.5 for the video end-to-end.
๐ญ Got a glimpse of it in 2022: one code block every 3 seconds. Four years later, Astra and Opus ship whole apps, build 3D scenes and can edit videos.