Our mission is to create frictionless audio experiences through coding. Video is a very important part - since video is often connected to audio.
Video creation itself is already widely accessible: There are stock videos you can use to create your content and there are audio libraries with royalty-free music, many of them free. You can even use text-to-speech voice-overs if you don’t want to narrate the content yourself.
Now, with api.audio, you can do all of that programmatically through our api. Not only is it faster and, as you will see, a lot easier, it also gives you the opportunity to integrate that functionality into your personal workflows.
Today I will show you how to create a new voice-over and background music for a Youtube video. The final product is a new version of your existing video. You can create as many of these as you want, using our script parameters to automatically create thousands of versions.
But let’s start with something simple. Feel free to explore the api.audio documentation and build your own, more complex version.
Let's consider a real world project or use case: Imagine you’re a real estate agency and you want to sell a property in London with a video walkthrough you’ve made, and you want to make that personalized to 30 potential buyers. That way, you can highlight the features you know will be important to each potential buyer and you can address each of them by name. That’s just one of the many possibilities to use this feature; you can go all in, automating and integrating it to your system if you want.
Before you start: Get your api key
It all starts with that. Here is how to do it: https://docs.api.audio/recipes/sign-up-here
1. Import packages
For Python, install FFmpeg with
sudo apt install ffmpeg or brew install ffmpeg. Then, pip install -U pytube aflr
npm install ytdl-core fluent-ffmpeg
yarn add ytdl-core fluent-ffmpeg
2. Create your speech with API.audio
Let's create some speech!
Remember to import your API key. If you haven’t done so already, you can get one here: https://console.api.audio/register
Now, choose a speaker and adjust the speed of the voice.
3. Download a video from YouTube
Let's download a video from Youtube.
4. Set up your video with speech
Combine the audio with your video!
5. Create your video with a voice over
Create a script for your voice over.
Paste in the url of the YouTube video you want to create a voice over for!
Check your local folder for your mp4 file!
That’s it! I hope you’ll like this feature and give it a go yourself. Any feedback is always appreciated of course.
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.