After voice cloning, AI can now generate sound effects from your hums

AI technology continues to evolve rapidly, with voice cloning being one of its remarkable achievements. By simply inputting any voice, the artificial intelligence technology can recreate that specific voice in almost its exact tone and speech.

Building on this innovation, Adobe Research and Northwestern University have introduced Sketch2Sound, an AI system that transforms vocal imitations and text descriptions into professional sound effects.

As per demos showcased by Adobe, this tool enables users to create audio by humming, making vocal sound effects, and using simple text descriptions.

 

 

 

 

View this post on Instagram

 

 

 

 

 

 

 

 

 

 

 

A post shared by Artificial Intelligence (AI) • ChatGPT (@chatgptricks)

Sketch2Sound analyzes the loudness, timbre, and pitch of vocal input, combining these characteristics with text to generate desired sounds. For example, entering a "forest atmosphere" and making short vocal sounds will result in bird calls without needing specific instructions.

Users can also create drum patterns by inputting phrases like "bass drum, snare drum" and humming rhythms. This capability is especially beneficial for independent artists, who can quickly generate sound effects for films and TV shows using their voice and text descriptions.

ALSO READ: “It’s hunting humans!” Forget jobs, AI is coming for all of us, warns ‘Godfather of AI’

As such, it will become extremely simple for users to generate audio through text prompts, object recognition, or by mimicking the desired sound with their voice, eliminating the need for paid sound effects or custom equipment, which often cost a fortune.

ALSO READ: AI courses across disciplines in AICTE institutions soon

While Adobe has not announced when exactly this product will launch, it may soon enhance popular software like Adobe Premiere, offering creators an efficient way to elevate their video projects with high-quality audio.