How To Use Kits AI Speaking Voices

Opening Up a New World

While most people turn to Kits.ai to enhance their music productions, there’s a whole other side to the platform worth exploring. Our royalty-free and Community Voices speaking models open up a world of possibilities for creators working outside music. Whether you’re crafting audiobooks, producing podcasts, or adding flair to your YouTube voiceovers, these tools can bring dynamic character and personality to your work, keeping your audience engaged from start to finish.

Today, I’m diving into how Kits.ai speaking models can elevate your storytelling, using the timeless tale of Little Red Riding Hood to showcase their versatility. I’ll be transforming my voice into multiple characters to bring more drama and intrigue to help tell the story.

Telling a Story

Little Red Riding Hood, A Brothers Grimm classic published in 1812, is a perfect example for demonstrating voice-driven storytelling. The story follows a girl, nicknamed Little Red Riding Hood, as she sets off to deliver a basket of goodies to her grandmother. Along the way, she meets a cunning wolf who tricks her into revealing her destination. The wolf reaches the grandmother’s house first, eats her, and disguises itself with her clothes. When Little Red arrives, she senses something is wrong–but the wolf’s plan is already in motion.

And then comes the most iconic part of the story:

• Little Red: “What big eyes you have, Grandmother!”

• Wolf: “The better to see you with, my dear.”

• Little Red: “What big ears you have, Grandmother!”

• Wolf: “The better to hear you with, my dear.”

• Little Red: “What big teeth you have, Grandmother!”

• Wolf: “The better to eat you with!”

Now, imagine recreating this classic scene, giving each character a distinctive voice to amp up the drama–all with just your voice and Kits.ai.

Recreating the Drama

Here’s how I brought this story to life:

Step 1: Record Your Dialogue

I recorded the dialogue in my natural voice, keeping Little Red’s lines lighter and in a higher pitch, while giving the Wolf a deeper, more sinister tone. Separating the delivery like this made it easier to enhance the characters during the conversion process.

Step 2: Prepare Your Audio

Next, I duplicated my track and separated the two characters by muting the sections that didn’t belong to each. Once I had clean, individual tracks for Little Red and the Wolf, I bounced them as separate files and got ready for the fun part: auditioning voice models!

Step 3: Choose Voice Models

• For Little Red: After trying out five different female speaking models, American Female Empath stole the show. To make the voice even more youthful and light, I raised the pitch by +7 semitones before smashing the “Convert” button.

• For the Wolf: I went with the Low Electronic model, typically used for deep, resonant spoken word in genres like Dubstep. It’s rich tone was perfect for the Big Bad Wolf. To add extra menace, I dropped the pitch by -7 semitones. 

Choosing the right voice model is crucial for achieving the desired character voice. The advanced AI technologies behind these voice models create lifelike and expressive speech, adding emotional nuances and personalized features.

Step 4: Add the Finishing Touches

With the voices converted, I imported both tracks back into my DAW. Adding a touch of room reverb helped create the atmosphere of the grandmother’s cabin, pulling everything together for a polished, dramatic result.

Check out the before and after to hear the transformation.

BEFORE: Original Audio

AFTER: Kits Processed

Conclusion

By using Kits.ai speaking voices, I was able to turn a simple recording into a dynamic, cinematic experience–all with just my voice and a bit of creativity. Whether you’re narrating a fairytale, producing an audiobook, or bringing characters to life in your YouTube videos, Kits.ai speaking models offer endless possibilities to enhance your storytelling.

Why settle for ordinary when you can captivate your audience with unique, expressive voices? With Kits.ai, the only limit is your imagination.

-SK

Sam Kearney is a producer, composer and sound designer based in Evergreen, Colorado.