Fish Audio S2 Pro

INT21's agent swarms have built inference stacks for video, music, and speech generation, now live as free demos without an API key. The stacks require no human review and outperform state-of-the-art …

Inflect v2, a text-to-speech model under 10 million parameters, achieves competitive performance with 4.395 UTMOS22 and 3.99% semantic WER for the Micro version (9.36M parameters) and 4.386 UTMOS22 wi…