D-ID Studio uses Stability AI’s deep learning face animation technology and GPT-3’s text generation to create and animate avatars or images using text prompts. We take a look at some of the really cool tools they have to see if they’re as good as they claim.
The main selling point of D-ID is that it enables you to animate a face and have it speak your script in a way that catches and holds the attention of your audience. Normally, if you wanted to do this, you’d need to hire a model and use a camera and lighting equipment to film the shot. After a few takes and some editing, hopefully, you get what you wanted.
D-ID takes you from idea to finished video while cutting out all the in-between effort you’d normally have to go through. D-ID has a few different AI image animation tools. Let’s check them out.
This is their flagship offering that creates animated video presenters. On the home page of their site (studio.d-id), you click “Generate Video” in the left menu panel, and you’re presented with a simple interface.
You can select a presenter avatar from their built-in realistic human options or illustrated ones. You can also create your own avatar if you prefer by clicking on “Generate AI Presenter.”
This allows you to enter a description of the presenter you want, and then Stability AI does its magic to generate it. Simply describe the type of avatar you want and watch as a one-of-a-kind presenter is created for you.
You can also create an avatar in your favorite AI face generator like DALL-E or NightCafe and then import the image into D-ID. It will animate that avatar in the same way it does for the built-in ones.
In the script section, you can type the text that you’d like your presenter to speak. Do you have an idea of what you’d like to say but can’t find the right words? The built-in AI text generator will do that for you.
The paid plans also give you the option to upload audio that can be converted into a video presenter.
Once you’ve got your script nailed down, you’ll want to hear how it sounds. You can choose from over a hundred languages and even different accents. The accents are great for customizing your video to suit your local audience.
You want the voice to match your presenter, and the app allows you to choose from multiple male and female voices with different tones. Some of these voices also have associated inflections and emotions. So depending on the message you’re conveying, you could choose a happy, excited, or even a more serious or formal voice.
D-ID doesn’t have a built-in translator, but it’s easy enough to copy and paste your English text into Google Translate. Paste the translated text back into D-ID and select the language there to have your script spoken in that language.
The accents and different languages sound really good. This is such a cool feature if you’re trying to duplicate your video for different international audiences quickly.
While the animation and the voices are really good, the end result is still obviously AI-generated. If you play around with different faces and get a good match with the voice options, you can improve the result though.
We’ve all used chatbots, but even the clever AI ones can seem a little impersonal. Chat D-ID allows you to add a human face and voice to your chatbot. Now, instead of your customer just reading text responses, they can have a human face to look at while they hear the responses spoken in their own language.
The free option gives you a good feel for what this animated chatbot can do. It allows you to chat with 5 different digital persons with 6 back and forth interactions.
If your company wants to stand out and offer more personalized chatbot experiences, then its paid API integration is worth considering. Pricing depends on the size of the organization and the type of enterprise solution your company needs.
This tool takes a portrait photo and animates it just a little to give it a little life. It’s good fun to take a photo of Grandpa and see him move a little, but there are some really useful uses for this technology too.
- Social media – bring photos to life and share them on social media
- Genealogy – Imagine taking an old photo of a long-deceased relative and animating their photo.
- Culture – Take well-known photos of celebrities and cultural icons and animate them.
- Documentaries – Bring still-life photos of historical figures to life to add a new dimension to your documentary projects.
D-ID Pricing Options
The 14-day free trial of DID Creator Studio gives you a really good idea of the capability of the tool and allows access to most of the functionality. If you’re happy to sign up for a paid plan, your options are:
- Lite – $5.99/month
- Pro – $49.99/month
- Advanced – $299/month
- Enterprise – customized pricing
The different plans all offer the same basic functionality but with a few small differences:
- Presenters – The Lite plan offers only standard presenters, while Pro plans and up offer premium presenter portraits.
- Licensing – The Lite plan is for personal use, while Pro and above offer commercial licensing.
- Watermark – The Lite plan has a “D-ID” watermark, while Pro and higher plans have a less obtrusive “AI” watermark.
- Moderation – D-ID is aware of the potential ethical issues with using its product. The automated moderation on the Lite and Pro plan may be a little overeager, while the higher paid plans offer manual review when it gets it wrong.
- Voices – The Lite and Pro plans have limited voices, while the Advanced plan gets you access to all of them.
- Credits – 1 credit is used for every 15 seconds of content created. Additional time is rounded up to the nearest 15 seconds. The Lite, Pro, and Advanced plans give you 40, 60, and 260 credits, respectively.
Powerpoint addon – If you want to create animated presenters directly in Powerpoint, then you’ll need to opt for the Advanced plan.
We love this tool and can already think of loads of applications where people could use it. If you’re in marketing, training, or corporate communications and want to create a quick, engaging video for your audience on YouYube or social media, then it’s perfect.
As a stand-alone tool, D-ID Creative Reality Studio works really well, but it also integrates with Canva. The Powerpoint and API integrations are also attractive prospects for larger companies. The different spoken languages and accents make it stand out from similar tools.
Sign up for their free trial and give it a try. There’s hardly any learning curve, so you’ll probably have your first video done in 5 minutes.