Creating with VARCO Sound

Generate by text input, generate by image upload, generate by video upload!

Today marks the start of the sound generation part! Having warmed up through previous posts, it’s now time to bring the sounds floating in your mind directly into VARCO Sound.

There are three main ways to generate sound in VARCO Sound.

First, Generate by Text Input

The most basic yet flexible feature is 'Generate by Text Input (Text-to-Sound)'. The text generation method is very intuitive. Just like asking ChatGPT, Gemini, or Claude, you simply need to input a description of the desired sound into the text box.

When working on game or video sound, there are times when you need specific sounds like "heavy footsteps echoing in a cave" or "sharp sci-fi impact sounds clashing grotesquely". In the past, you would have spent a lot of time rummaging through a vast sound library to find samples, bringing them into a DAW like Cubase to tweak the pitch and add reverb.

But with VARCO Sound, you just need to write it in the prompt.

The more elements you add to describe the sound, rather than simply writing "footsteps" or "gunshots", the more detailed the results will be.

Once you input the text, multiple sounds are generated at once, so you can choose one to use, layer several sounds, or edit them freely.

Second, Generate by Image Upload

One of the innovative features of VARCO Sound is the 'Generate by Image Upload (Image-to-Sound)' function, which allows you to generate sound using only visual information. When you upload a game screenshot or concept art image, it recognizes the objects and creatures present and analyzes the scene's environment (indoor/outdoor, weather, time of day). After grasping the overall atmosphere and tone, it automatically generates natural ambient sounds and sound effects based on all this information. At this point, it also suggests multiple versions of sounds for the user to choose from.

The generated sounds can be played directly over the image. Simply drag and drop the image of the subject you need to work on into VARCO Sound to upload it. It analyzes the visual information and generates the corresponding sound automatically.

Additionally, while a great sound can be generated with just one image, adding a little of the 'text prompt' we learned earlier enhances the detail. Instead of just uploading the image, try adding a specific situation in text like "the sound of a penguin jumping and bouncing a basketball". Combining the visual image with specific text can yield vibrant sounds.

Third, Generate by Video Upload

This is the ultimate feature known as 'Generate by Video Upload (Video-to-Sound)'.

Anyone who has done sound design or video editing can relate. When adding sound to trailers or in-game cutscenes, uploading the video to a DAW or video editing program and matching the timing frame by frame is an incredibly time-consuming and labor-intensive process.

However, the video upload generation feature of VARCO Sound precisely analyzes the detailed movements of objects over time and each timing.

Just upload the video you want to work on, and it scans the movements of the characters in the video frame by frame. There’s no need for the user to manually drag audio waveforms to match; the AI accurately aligns the visual impact points with the sound timing.

As you can see in the image above, the video upload generation feature provides an automatically generated 'multi-track' structure tailored to the video. The AI generates and layers background ambient sounds, effect sounds, impacts, and mixes them all together in one multi-track composition based on the situation in the video.

---

We have looked at the three generation methods provided by VARCO Sound.

What did you think? Instead of spending time rummaging through a vast sound library or syncing sounds, you can now invest more time and energy in the essence of sound design, pondering 'what sound would make this scene more vivid'.

Beyond just reading, I encourage you to use this article as a guide to open VARCO Sound and create your first AI sound!

In the next part, we will explore various features of VARCO Sound, including variations, creature sounds, and music generation.

Previous Part ← Part 2, Creating with VARCO Sound - Generating Sound from Text / Image / Video

Next Part → Part 4, Using VARCO Sound - Utilizing Variations to Creature Sounds and More

Try Creating While Reading

→ Start with VARCO Sound