The landscape of generative audio is shifting toward efficiency. A new open-source contender, Kani-TTS-2, has been released by the team at nineninesix.ai. This model marks a departure from heavy, compute-expensive TTS systems. Instead, it treats audio as a language, delivering high-fidelity speech synthesis with a remarkably small footprint. Kani-TTS-2 offers a lean, high-performance alternative to
The post Meet ‘Kani-TTS-2’: A 400M Param Open Source Text-to-Speech Model that Runs in 3GB VRAM with Voice Cloning Support appeared first on MarkTechPost. Read More
