Kling AI, an AI video generation tool developed by Chinese short video giant Kuaishou, has rolled out a new feature that automatically generates sound effects synchronized with video visuals.

The new functionality, available across Kling AI’s video models, aims to provide users with a more immersive content creation experience. It allows for the simultaneous generation of videos and their corresponding soundscapes.

Additionally, the platform has upgraded its existing sound effect generation feature, introducing a “video-to-sound effect” module. This module enables users to upload their own videos or leverage historical works to automatically match them with suitable sound effects.

This capability is powered by Kling AI’s proprietary multimodal video-to-sound effect model, Kling-Foley, which is designed to achieve frame-level alignment between audio and visual content.

🔗 Source: AI Base

🧠 Food for thought

1️⃣ AI sound generation follows century-long evolution in audio technology

Keling AI’s new feature represents the latest chapter in sound design’s long history, extending from manual theater sound effects to AI-generated audio.

The original foley technique, creating synchronized sound effects for visual media, dates back to radio broadcasting in the 1930s, with the BBC publishing an article in 1931 emphasizing sound effects’ importance in storytelling 1.

This progression has evolved through distinct technological eras: from acoustic recording (1877-1925) to electrical (1925-48), magnetic (1948-80), and digital (from 1972) 2.

Sound design’s recognition as a creative discipline rather than merely technical work began when Walter Murch was first credited as “Sound Designer” for “Apocalypse Now” in 1979 3.

Keling AI’s frame-level alignment technology reflects a pattern seen throughout sound design history, where each technological advancement has aimed to create more precise synchronization between visuals and audio.

2️⃣ Competitive differentiation through multimodal AI capabilities

Keling AI’s integration of audio effects into video generation highlights how AI companies are racing to create more comprehensive creative tools.

Recent market analysis shows significant price differences among competitors, with Kling 2.1 (likely the same company as Keling AI with different romanization) offering its audio-video tool for approximately $9 compared to Google’s Veo 3 at $250 4.

Early user feedback specifically praises Kling’s audio-visual synchronization capabilities, highlighting the effectiveness of its proprietary Kling-Foley model in generating realistic soundscapes that match the visual content 4.