Keling 2.6 is now fully available! Hear the visuals and see the sound!

Keling 2.6 is now fully launched, featuring its first "audio-visual simultaneous generation" model. It can generate visuals, natural speech, matching sound effects, and ambient atmosphere in a single output. The model supports two creation paths: text-based audio-visual and image-based audio-visual, and is suitable for various applications such as monologues, narration, multi-person dialogues, musical performances, and creative scenarios.