A few weeks back we introduced our publicly available voice library, with over 250 voices and counting from 7 providers, including Amazon, Microsoft Azure and Google. Why is this great? Because with just one api, you get access to all of these voices without the need to maintain or update each single api from each provider.
However, api.audio’s mission is really to make the whole audio production process scalable, so we’ll need more than just speech.
This is why we’re introducing our Sound Library: it's much more than you might think.
Sound engineers will introduce sound elements to your track depending on what you’re trying to convey to your listeners. This is why we speak of sound designs, not just background tracks.
Sounds on api.audio are not just background music, but dynamic audio segments. Good audio production doesn’t just run a background track with some voice over. Instead, sound engineers will introduce sound elements to your track depending on what you’re trying to convey to your listeners. This is why we speak of sound designs, not just background tracks.
With the Aflorithmic sound library we wanted to build something similar to what a sound engineer would do when creating audio, but make it programmatically available, so it can scale up and drive cost down.
How do we do that? In its simplest form, a sound design in the Aflorithmic library is divided into 3 parts. When you write the script for your tracks, you can use these sound design parts for each segment of the audio story you’re telling to your listeners.
The sound design of your story should follow your structure. For instance, if you are using a simple Intro, Main and Outro story structure, this is what each sound design segment can help you achieve:
This is your attention grabber. You’ll want to make sure people listen up when your track or spot is playing. If you‘re producing a track that goes in between other audio tracks, the intro also helps you draw a line between each of them, telling the listener that a new track has just started.
Here you’ll explain your point or introduce a problem followed by your solution. It’s what most people would call a classic background track. Due to the recommended storytelling structure for audio, this will most likely be the longest part of your track.
Time to wrap things up! In the outro you’ll want to use your brand, claim, or just a conclusion for your audio track and leave listeners with something they’ll remember.
These are once again attention grabbers. Effects work perfectly for emphasizing words or sentences, so that the listener understands and remembers specific parts of the track.
The sound designs in our library have been thoughtfully created with specific purposes and use cases in mind. For example, “Breaking News” is designed to create an engaging newscast, while “Haute Cuisine” is a great sound template for a food commercial or a recipe. You can use the filters on the top of the page to narrow down and select what you’re looking for.
Last but not least, api.audio is an infrastructure to build scalable audio for developers and we wanted to reflect that. This is why you can easily just copy/paste the code for each sound design template and paste it into your own code when developing a project with api.audio.
At the time of writing there are 39 sound design templates for creating scalable audio in Aflorithmic’s sound library and lots more are coming. Try them all on https://library.api.audio/sounds
Do you want to know more?
- Api.video + api.audio: Localize Advertisement Videos with Personalized Voice Overs
- Introducing: The World’s Largest Artificial Voice Library!
- Creating Personalized Audio Ads
- How To Create Engaging Voice Over For Your Video
Aflorithmic is a London/Barcelona-based technology company. Its api.audio platform enables fully automated, scalable audio production by using synthetic media, voice cloning, and audio mastering, to then deliver it on any device, such as websites, mobile apps, or smart speakers.
With this Audio-As-A-Service, anybody can create beautiful sounding audio, starting from a simple text to including music and complex audio engineering without any previous experience required.
The team consists of highly skilled specialists in machine learning, software development, voice synthesizing, AI research, audio engineering, and product development.