Forum Discussion
New in Labs: AI Avatars
AI Avatars is in active development as part of Labs. Functionality will evolve, and we may modify or remove certain features based on user feedback and stability. This feature is only available if AI Assistant is enabled in your subscription.
Creating videos the old-fashioned way—recording, editing, and then re-recording as content changes—slows down course development and makes it harder to keep lessons consistent. Now, with AI Avatars in Rise 360, you can turn your scripts into presenter-style videos using a customizable character. Creating, updating, and reusing video content has never been easier! Keep reading to see how it works.
- Understand AI Avatars
- Generate AI Avatars
- Get Better Results with These Tips
- Usage and Credits FAQs
- Share Your Feedback
Understand AI Avatars
AI Avatars work best for short, presenter-style videos. Lesson introductions, transitions, and key takeaways can all benefit from a consistent voice and presence to guide learners through content.
Create your own character or choose from a library of photorealistic and illustrated characters. You can filter by style, gender, age, or environment and customize your chosen character through a simple chat interface.
While the AI Avatars feature is included in your Articulate 360 AI subscription, generating AI avatar videos uses credits. (Learn how credits work.) You’ll be able to see how many credits you need before you generate.
Note: Credit usage depends on the length of your video, up to a maximum of five minutes.
In the next section, find out how to create your first AI avatar video. Then, explore tips and known limitations to get the best results.
Generate AI Avatars
To get started, go to a lesson in your course and click Block Library in the shortcuts bar at the bottom. This opens the block library as a sidebar menu on the left. Then, click AI blocks > Generate AI avatar to open the AI Avatars workspace.
AI Avatars workspace with character and voice selection panels on the left, and character preview on the right.
You can either select a character to use as-is from the Character library, customize a given character, or create one of your own.
Select a Character
- Choose a character in the Character library tab within the character selection panel.
- Use Filters to find specific characters. The available filter options include:
- Style: Photorealistic, Illustrated
- Gender: Female, Male, Non-binary
- Age: Young adult, Adult, Older adult
- Environment: Office, Medical, Construction, Industry
- See your currently selected character in the preview panel on the right. From here you can:
- Download the character by clicking the Download icon. (Characters download in PNG format.)
- Edit your character by clicking the Customize button.
Customize or Create a Character
To customize an existing character, select it and click Customize in the preview panel. To create a new one, click Create new character in the Character library tab. Both options open the character customization interface.
Enter your prompt in the chat box to describe the character or the changes you want. You can ask to do things like:
- Changing the background or setting
- Updating clothing or appearance
- Modifying the character’s pose
- Adding or removing elements
AI Avatars character customization chat interface
If you’re creating a new character, include as much detail as possible. Include your desired character’s role or job, clothing, or setting and the overall visual tone. In the future, we’ll add prebuilt options to speed up character creation.
As you iterate, new versions appear in the preview panel. Use the filmstrip or arrows to switch between versions and compare results.
When you’re ready, select a version and click Save character. Enter a name, then click Save. Your character will appear under the Saved characters tab.
Click the X icon in the upper right or the back arrow in the upper left to return to the AI Avatars workspace. If you leave without saving, your changes will be lost.
Note: Currently, you can’t rename or delete a saved character.
Add Character Voice
Use the audio selection panel to generate text-to-speech audio for your character. If you’ve used AI text-to-speech in Rise 360 before, this experience will feel familiar.
To choose a voice and create your audio, follow these steps:
- Select a voice from the dropdown menu.
- If you’re using a character from the library, a recommended voice is selected by default.
- Open the dropdown to explore other options.
- Click the play button to preview a voice.
- Click View all voices to browse the full voice library.
- Add your script.
- Enter your script in the text box.
- To generate a script, click Write with AI and enter a prompt or choose from prebuilt options.
- Scripts can be up to 5,000 characters long.
- Configure advanced settings (optional).
- Click Advanced settings to choose a voice model or make further adjustments.
- Generate speech.
- Click Generate voiceover to create the voiceover.
- Each version is saved in the History list on the bottom left for easy comparison.
- Use the static preview on the right to check how the voice pairs with your character.
Generate Avatar Video
When you’re satisfied with the character and voice pairing, click Generate with [X] credits in the bottom right to create the avatar video. The credit usage is shown on the button, and your remaining credits appear next to it.
You’ll see a placeholder block while AI Assistant generates your video. A progress bar also appears in the bottom-left corner. You may continue working while this is in progress.
To edit your video, hover over the block, click Content, then click the Replace with AI Avatar icon in the sidebar menu. This will reopen the AI Avatars workspace, allowing you to update the character, voice, or script.
Get Better Results with These Tips
The following tips will help you get better, more consistent results when creating AI Avatar videos:
- Keep content simple. Complex scenes with multiple characters or busy environments can lead to unnatural lip-syncing and background movement. Focus on videos that work well with single narrators, such as introductions, transitions, and key takeaways.
- Keep videos short. Videos can be a maximum of five minutes. Shorter presenter videos (less than 2 minutes) produce the best results.
- Make prompts clear and specific. Describe exactly what you want, including details like the character’s role, appearance, and environment.
- Focus on one idea at a time. Break longer content into individual avatar videos, each delivering a single message.
Understanding the following known limitations can help you get more predictable results:
- Generation takes a while. We’re prioritizing output quality, which can increase processing time—especially for longer scripts. We know this can feel slow, and we’re continuing to look for ways to improve the experience.
- You may see excessive or unwanted hand motions. Characters may sometimes gesture more with their hands than expected.
- Background movements might appear unnatural. You may notice subtle motion in the background, even when it’s supposed to be static.
- AI avatar video could trail off. Your video may end abruptly or trail off without a natural pause in the narration.
These are known limitations of the model and cannot be resolved through prompt adjustments. We are working to improve these experiences.
Usage and Credits FAQs
What is a credit? How does it work?
Each time you create or regenerate an AI Avatar video, a small number of video generation credits will be used. You’ll always see exactly how many credits a video will cost before you generate it.
As part of the Labs experience, you’ll have a fixed number of credits to explore and create.
What happens when I run out of credits?
This experience currently includes a fixed number of credits. If you use yours up and would like more, you can apply to join our private beta. If you’re accepted, we’ll provide additional credits in exchange for participating in feedback sessions to help us improve the feature. Learn more about our beta and trial terms.
Do credits get used every time I edit or duplicate avatar video blocks?
Credits are only used when regenerating a video; duplicating avatar blocks or editing without regeneration doesn't consume credits.
Are failed generations refunded? How about low-quality or unexpected results?
If a generation fails, the credits used are automatically refunded, allowing you to try again. During this Labs phase, credits won’t be refunded if results don’t meet expectations.
Can credits be shared across a team?
No. Credits are tied to individual users and can’t be shared.
Can admins control or limit usage?
Usage controls are not available during this Labs phase.
Share Your Feedback
We’d love to hear how the AI Avatars feature is working for you! After generating a video, use the feedback prompt in the lower-right corner to rate the result. Click the thumbs-up icon if it meets your needs, or the thumbs-down icon to share your thoughts. Either way, your input goes directly to our product and engineering teams to help improve the experience. You can also use this feedback survey link or share your thoughts in the comments below.
67 Replies
- MeeraLynn-UKCommunity Member
Hi. Do you have a roadmap to the full release of the AI Avatar function please? Thanks.
- CarmenWatermanCommunity Member
I am really excited about this new feature. It is something I have been looking for and have tested some other leading providers of ai avatars for text to voice avatar. I will be testing and am sure to use up my credits. I am happy to provide feedback as well.
- CarmenWatermanCommunity Member
More on this next week, but I tried it for the first time and love it. I'm working on a new project right now and this is perfect timing for me to add something that our learners have been waiting for.
Hi, CarmenWaterman!
I'm so glad you're trying this out! We'd love to hear your feedback and answer any questions.
- SarahDmowskiCommunity Member
I just to provide feedback when prompted in the block itself, but I got stuck in an endless loop of the questions. Once I reached the end, it directed me back to question 5 and I couldn't get to the end to submit. Here is the main feedback I had:
This is more so feedback on the voices themselves but factors heavily into the Avatar block:
1 - Make it easier to search for voices with expanded filters; the biggest one would be for nationality/accent (e.g. American, British, Hindi, Brazilian, etc.). Adding additional filters helps to narrow down the options a lot easier and then the search field can be used to locate very specific parameters rather than something broad like "American".
2 - Save our search by default; after filtering/searching to return a specific set of results and going back to generate the voice, I would love for those results to be saved when I go back in to select a different voice. Then, just add a button to clear search results if desired.
3 - Sometimes the preview voice sounds a lot better than generating our own content. For example, I used "Lauren B." and the preview sounded very conversational, with tone and inflection, and sounded like a real person. The generated voice almost sounded like a different person - very flat, monotone, and generic.
- JasadaSmithCommunity Member
Im really unhappy, I have so much work to do , and have been procrastinating and playing in this space instead of doing my work. Seriously outstanding job on avatars, the range of voice overs is outstanding and this brings a whole new vibe to a Rise course
We love to hear that you're enjoying AI Avatars, JasadaSmith! I hope this helps speed up your workflow!
- Chris-HurstCommunity Member
It would be great if there was a Transcript feature in the video player, the same as there is in the Storyline video player.
- CherylStGermainCommunity Member
I echo the ability to have a Transcript. I only created a short video, but the sync on the audio to the avatar was not great. I currently use an external software to create these types of videos and then import them, and for now I will continue to do so, but will continue to play with this as updates are made.
- Chris-HurstCommunity Member
In Rise I use a one drawer accordion for the Transcript, but it's clunky and would be better UX if it was integrated in the player toolbar.
Hi Chris-Hurst and CherylStGermain,
Thanks so much for sharing. I can see how implementing a transcript feature would be helpful to your workflow!
- christiebentleyCommunity Member
Is there the opportunity to share avatars that are created to suit your brand with a team of users to maintain consistency? or would the description to create the customized avatar have to be used by each individual? would this then create variations of the same avatar that would all be slightly different?
Hi christiebentley,
Thanks for reaching out!
Currently, there's not an option to share an avatar you created directly with other team members. One idea is to share a copy of your Rise course with another user, so they'll have access to the avatar there. I can see how this enhancement would be helpful when collaborating on courses, and especially to maintain consistency.
- TammyKnoll-AndeCommunity Member
First off, holy moley! If this pans out as I hope it will (fingers crossed), this feature would replace at least two other tools I'm paying for!
Here are my thoughts on my first attempt. I wasn't sure what to expect or where to prompt for the video action. This attempt cost 25 credits for 25 seconds of video.The character and VO worked well, but the action was all wrong. The character is an instructor for an in-person class, but the audience is taking a Rise eLearning course (confusing, I know).
The generated video included a monitor screen with virtual learners, which she pointed at the entire time. She completely ignored the whiteboard and students in front of her while looking directly at me!
The in-person learners were the most interesting part of this as they nodded their heads and spoke in sync with the instructor to the audio script. Since this was my first attempt, the process wasn't obvious where to prompt for the character and in-person learners' movements or actions.
Additionally, I second SarahDmowski's feedback related to VO. The most important new filters would be for accent and language. Once I've identified the demographic, I'd like to filter by rating (the number of people who used the specific voice).Hi, TammyKnoll-Ande!
Thank you so much for sharing your experience so far, and letting us know that filtering by rating would be helpful to you! Please don't hesitate to reach out with any other feedback as you create!
- servicedeformatCommunity Member
Hello!
I’m very excited about this new feature! I was able to generate a video in just a few minutes. 😃
As for the synchronization between the voice and the mouth movements, there may be some room for improvement, but overall it’s very good.
It would also be interesting to have the option to upload an image in order to create a character.Hi, servicedeformat!
I'm so glad to hear you're enjoying this feature. I've logged your feedback internally!
- CaroleEmard1Community Member
In Vyound, you can add a still image of a person, and then it renders a talking head and it is quite good. I hope this will be available here.
- SMcNicolCommunity Member
You can do that with AI Avatars, just go to upload character and add your image. 😀
- FrostwornCommunity Member
I just used the block to generate a video 49 seconds long. It took about 10 minutes to generate. I used the provided Avery avatar with Jessica Bogart's voice. Even though I'm highly perceptive, I think anyone would agree the result was goofy. The lip-syncing was off most of the time, she opened her mouth wide several times, and the mouth, teeth, and eyes changed in size and sharpness frequently--feeling more like Elastigirl. The teeth morphed together a couple times (something AI has had a particularly hard time with).
As my favorite YouTube home inspector likes to say, "If you squint, it's mint."
All that said, it is very close to passably human. There are moments when the avatar is sharp and in sync, and that gives me hope. This is a really cool idea and I hope it succeeds. I agree with all of the feature requests my colleagues have already stated.
With or without avatar video, I also want the ability for AI voice to narrate an entire course, much like Microsoft Edge's "Read Aloud" feature, with a floating set of audio controls which follows you as you scroll.
Hi Frostworn,
Thanks so much for sharing your feedback and including screenshots! I see what you mean about the teeth and wide mouth. I've passed this along to our team.
Please feel free to share with us here, or use this feedback survey link as you continue testing this feature!
Related Content
- 2 months ago
- 14 days ago
- 2 months ago
- 3 months ago
- 2 months ago