a sunny day at the beach. a sand sculpture of boombox. the word “Audio” is drawn in the sand –ar 5:3 –style raw
Cartesia: Announcing Sonic: A Low-Latency Voice Model for Lifelike Speech
“Sneak preview (coming soon to a device near you)
“On speech, a parameter-matched and optimized Sonic model trained on the same data as a widely used Transformer improves audio quality significantly (20% lower perplexity, 2x lower word error, 1 point higher NISQA quality).” / X
Sonic Demo
“Interesting experiment from Google that creates an NPR-like discussion about any academic paper. It definitely suggests some cool possibilities for science communication. And the voices, pauses, and breaths really scream public radio. Listen to at least the first 30 seconds.
Suno
“v3.5 is now available to all users! 🥳 Now everyone can: • Make 4-min songs. You can now get your full song in a single generation! • Create 2-minute max song extensions • Experience improved song structure and vocal flow Your feedback is important to us, and helps us” / X
“Make a song from any sound. Coming soon 🎧 VOL-1: A watering can, but make it psychedelic rock
“Make a song from any sound. Coming soon 🎧 VOL-2: Classical piano, and bring in some French accordion Performed by Anessa (Pianist and Suno Software Engineer)
“Can I just say I loooove Suno. Some of my favorites: Dog dog dog dog dog dog dog dog woof woof
Udio
“Today we’re delighted to launch more new features, starting with a model capable of two-minute generations, udio-130. This makes it much easier to create tracks with long-term coherence and structure. Check out the track below for a taste of what’s possible using a single https://x.com/udiomusic/status/1795834878983803341
Leave a Reply