Create Custom Realistic AI Avatars That Look & Sound 100% Like You (Full Workflow) — Transcript
Full transcript
- 0:00Imagine you could create a custom AI
- 0:01avatar that looks so real that people
- 0:03didn't actually know it was you. Well,
- 0:05you can. What you just saw was a digital
- 0:07clone of myself that looks and sounds
- 0:08100% like me. And if you didn't notice,
- 0:10it's because I created it using the 11
- 0:12Labs creative platform. There's a lot of
- 0:14different AI tools out there nowadays,
- 0:15but when it comes to creating AI avatars
- 0:17and cloning yourself, the quality is the
- 0:18most important thing. And thankfully, 11
- 0:20Labs provides all of the best AI image
- 0:22and video models out there and voice
- 0:24clone technology, allowing you to make
- 0:25the most realistic AI avatar clones out
- 0:27there.
- 0:27>> What do you think? Believe it or not,
- 0:30I'm [music] also an avatar from 11 Labs.
- 0:33>> And now, if I put myself side by side
- 0:34with my AI avatar and I lip-sync the
- 0:36audio, can you really spot the
- 0:38difference? And the cool thing is is
- 0:39that you can even change the clothes and
- 0:41put yourself in any environment. So, I
- 0:42decided to make myself look much smarter
- 0:44than I actually am. Hey everyone, my
- 0:46name is Alec and today I'm about to show
- 0:48you how to get the most realistic clone
- 0:49of yourself so you can simply type out
- 0:51what you want on your keyboard and
- 0:52create your video without having to go
- 0:54through the painful process of
- 0:56recording. So every take from now on is
- 0:58going to be perfect. Let's begin. Now
- 0:59with 11 Labs, you can create avatars
- 1:01that look 100% like you or you can make
- 1:03entirely AI generated avatars and you
- 1:05can even do a mix so you can put
- 1:07yourself in any [music] environment. But
- 1:09first, let's take a look at how to clone
- 1:11your voice. So you can create voiceovers
- 1:12that sound like you without actually
- 1:13having to record them. To clone your
- 1:15voice, you need to click on voices. And
- 1:17then on the right, we want to click on
- 1:18create a voice clone. And here we have
- 1:20multiple options to clone our voice.
- 1:22First of all, we got instant voice
- 1:23clone, which allows us to clone our
- 1:25voice with a minimum of 10 seconds of
- 1:27audio. And then we have professional
- 1:29voice clone, which allows us to create a
- 1:31super realistic digital replica of our
- 1:33voice. And here [music] we need to
- 1:34submit a minimum of 30 minutes of audio.
- 1:36And now, the higher the quality of the
- 1:38audio you submit to your voice clones,
- 1:40the better the result of the voice clone
- 1:42will be. And so, if we click on
- 1:43professional voice clone, as you can see
- 1:45here, you simply want to click create a
- 1:47new clone. And now go through the
- 1:48process of uploading your samples. You
- 1:50can even record directly into 11 Labs
- 1:52and [music] then name your voice clone.
- 1:54And if you want an in-depth guide to
- 1:55creating the highest quality voice clone
- 1:57possible, we'll put a link down in the
- 1:58description below to a full 10-minute
- 2:00[music] guide that we've put together
- 2:01for you. Once you have your voice clone,
- 2:02we can then click on text to speech. And
- 2:04here we can type out anything that we
- 2:06want our AI avatar to say. And so here
- 2:09I've got a default script talking about
- 2:11coffee. But to use our voice clone, we
- 2:13can then click on voices. And here we
- 2:15can go ahead and search for our voice
- 2:16clone. But as you can see here, I've got
- 2:18my own professional voice clone that
- 2:19I've named Alex PVC. And so if I click
- 2:22on it, [music] I can now generate this
- 2:24text right here that I've typed in, and
- 2:26it will sound just like me. So, let's
- 2:28take a listen. Coffee is one of those
- 2:29things most of us consume every day
- 2:31without really thinking about it. And
- 2:33so, as you can see, I've now got a
- 2:35script that sounds just like me, and all
- 2:37I've done is typed it out. And so, I
- 2:39could go in and replace this with
- 2:41anything I like. And so, if I said,
- 2:42"Hello YouTube, please subscribe." We
- 2:44can then click on generate. Hello
- 2:46YouTube, please subscribe. And as you
- 2:48can see, we've now got Hello YouTube,
- 2:50please subscribe in my voice. And so now
- 2:53that you have your voice clone and your
- 2:55voice over, we actually need to make the
- 2:57AI avatar. And to do this, we can head
- 2:59to the image and video tool on the left
- 3:01right here. And with inside image and
- 3:03video, there's a bunch of different ways
- 3:04that we can use and create AI avatars.
- 3:06We can use default avatars. We can
- 3:09create our own from scratch, but we
- 3:11could also upload pictures of oursel and
- 3:13even customize those avatars to get the
- 3:15exact result that we want. And so to
- 3:16begin, let's start with the default
- 3:17model. If we switch to video in the
- 3:20generation model, we can then click on
- 3:22the video models and we can scroll down
- 3:25and we can select Creatify Aurora.
- 3:27Within Creatify Aurora, we have a bunch
- 3:29of default avatars that we can choose.
- 3:32And so let's say we decide to choose
- 3:33this one right here. I could then click
- 3:35on speech and here we can go and add the
- 3:39audio that we've just generated. So if I
- 3:41click the plus I can use this as the
- 3:42speech and now I can simply click
- 3:44generate and Creatify Aurora is then
- 3:47going to create an AI avatar video of
- 3:49the default avatar plus the audio that
- 3:51I've just given it which is my voice
- 3:53clone. But if you can't find an AI
- 3:54avatar you like, you could then actually
- 3:56go and create your own simply by
- 3:58prompting the avatar that you want in
- 4:00[music] the image generation model with
- 4:03any image generation model. And so we
- 4:05could select [music] a model like Nano
- 4:07Banana Pro here. I'm going to go ahead
- 4:09and then use this prompt. And this
- 4:11prompt is just to give you a little bit
- 4:12of inspiration, but you could go ahead
- 4:14and describe any AI avatar for any
- 4:16[music] use case that you like. So, it
- 4:18could be for a construction site, it
- 4:20could be for a scientist, it could be
- 4:21for a doctor. And you simply type out
- 4:23what you want. Here, I want to change
- 4:25the resolution to at least 2K, but I
- 4:27would recommend even going up to 4K
- 4:29because the better the input of the
- 4:30image we give to AI video generation
- 4:33models, the [music] better the output.
- 4:34And then I'm going to choose four
- 4:36generations just so I've got a choice to
- 4:37choose from. And then I simply click
- 4:40generate. And so, as you can see, now
- 4:41we've got four different AI avatars that
- 4:43we could choose from. And if you didn't
- 4:45like any of them, you could go and click
- 4:46on the prompt again, regenerate to
- 4:48iterate on top of it. But if you did,
- 4:50what we could do is switch back to video
- 4:52and then within the Creatify Aurora
- 4:54model, we could simply drag and drop the
- 4:56one that we like into the AI avatar
- 4:58space. And we could scroll down to our
- 5:00previous generation and simply click on
- 5:02the audio again to use the same one and
- 5:04then click generate. But for this use
- 5:06case, I want to make an AI avatar that
- 5:08looks and [music] sounds 100% like me.
- 5:10We already have the voice. So now all we
- 5:12need is a photo and an image of me. Now
- 5:14if I was to click on avatar and then I
- 5:17click on upload, I could open up an
- 5:19image of me and then simply click
- 5:21generate. And now I have an AI avatar
- 5:24video that looks [music] and sounds like
- 5:25me. But the problem with this video is
- 5:27that the image is one by one. And I also
- 5:29don't like the layout on the backdrop.
- 5:30It doesn't feel like it was recorded and
- 5:33shot. It looks like we've turned an
- 5:34image into a video. And so what we could
- 5:37do if we go back to the image generation
- 5:39model, I can paste in this [music]
- 5:41prompt this time. And so as you can see
- 5:43at the start, I've got use my likeness
- 5:44from the uploaded reference image. And
- 5:46then I'm going to upload that same image
- 5:48as the reference image [music] with Nano
- 5:50Banana Pro. And then I'm going to change
- 5:52the aspect ratio to 4K because again, I
- 5:54want a really good input for the AI
- 5:56video models. And now I've got a short
- 5:59description of what I want the setting
- 6:01to be like. So I'm putting myself in a
- 6:02[music] new environment. And here I
- 6:04could change my clothes. I can change
- 6:06the background. I can change the
- 6:07lighting. [music] Anything I like. And
- 6:09by the way, let me know in the comments
- 6:10down below what type of AI avatar you
- 6:13are making. I'm very curious and I would
- 6:14love to see what you guys make. And
- 6:16before I click generate, I do want to
- 6:17mention that you can adjust the aspect
- 6:19ratio. And so here I want to turn it
- 6:20into a 16x9 video, but we could also
- 6:22make this [music] a 9x6 video. If you
- 6:25were making a vertical short form
- 6:28Instagram reel or Tik Tok, this would be
- 6:31perfect. And if you want something a
- 6:32little bit more UGC looking, we actually
- 6:34have a full tutorial on how to make UGC
- 6:37videos with AI, and we'll leave that in
- 6:39the description down below as well. And
- 6:41so now that I've got my reference image
- 6:42and the prompt, we simply [music] click
- 6:44generate. And so, as you can see, now
- 6:46I've got four still images that look
- 6:48100% like me that I can use as my AI
- 6:51avatar. And so, I really like this one.
- 6:52The environment looks so much better
- 6:54than the previous one, and it looks like
- 6:56a YouTube video, which is the aesthetic
- 6:59I was going for. [music] And so then
- 7:00again, I could go back to Creatify
- 7:02Aurora and I could drag and drop this
- 7:05one in [music] as the AI avatar image
- 7:08that I want to use. And then again go
- 7:10and add the speech simply by clicking on
- 7:13the previous audio that I used. And I
- 7:16would then go ahead and [music] click
- 7:18generate. And now I've got a custom AI
- 7:20avatar that still looks 100% [music]
- 7:22like me and still sounds 100% like me,
- 7:25except I'm in an environment that I was
- 7:27never [music] in. And right now, I've
- 7:29been using Creatify Aurora for all of my
- 7:31generations. But I do want to talk about
- 7:32a couple of other models and their
- 7:34limitations to help you pick which one
- 7:36you can use. Because if you click here,
- 7:38as you can see, there's a bunch of
- 7:40different AI models that you can choose.
- 7:42And we've been using some from the
- 7:43lipsync category, [music] but there's
- 7:45three that I want to talk about. The one
- 7:46that I've been using for all the
- 7:47generations so far has been created by
- 7:49Aurora. And the reason I like this model
- 7:51is that it has [music] a maximum length
- 7:52of 60 seconds. However, the resolution
- 7:55is capped to a maximum of 720p, but it's
- 7:58very expressive and it's pretty good for
- 8:00stable talking avatars. [music] The
- 8:02minus of it is just that you always need
- 8:03to upscale it afterwards, which you can
- 8:05also do inside of 11 Labs as well. The
- 8:07next one is Omnihuman 1.5. This one's
- 8:10nice. It's got a maximum resolution of
- 8:121080p, but the duration is capped at 30
- 8:15seconds. It is really good at [music]
- 8:17realistic faces though, but the clips
- 8:20are a little bit shorter and there's a
- 8:21little less movement and expressiveness
- 8:23in the face. And then finally, we've got
- 8:26LTX audio to video, which recently came
- 8:28out. [music] And this one, you can do
- 8:30resolutions of 720p and 1080p, but the
- 8:33maximum length is 20 seconds. However,
- 8:36this is an audiodriven AI [music] video
- 8:38model, and so it's not strictly
- 8:40lip-sync. This means that you can add a
- 8:42custom prompt with it to guide what's
- 8:44happening inside [music] of the video.
- 8:46and it will take into account your
- 8:47prompt and the audio as [music] well as
- 8:49the AI avatar start frame that you've
- 8:52given it and you can get some really
- 8:53cool results with this. And if you think
- 8:55about it, there are so many different
- 8:56ways that you can use this AI avatar
- 8:58content creation workflow in your
- 8:59creative processes. And let me show you
- 9:01a couple of cool things. First of all,
- 9:02if you didn't want to create a voice
- 9:04clone, you could actually upload your
- 9:06own voice recording. And so you're
- 9:08essentially lip-syncing a real audio
- 9:10recording of your voice to an AI avatar.
- 9:13And that's one workflow that you could
- 9:14do. But then if you think about it, you
- 9:16could take it even further and here you
- 9:18could go to voice changer. You could
- 9:20then record your own audio directly into
- 9:22voice changer and [music] you could then
- 9:24swap it to a new voice. So here right
- 9:27now I'm recording. And then if I click
- 9:29stop, I could then go to the voices
- 9:31section and change it to any voice I
- 9:34like and get a completely new sounding
- 9:36version of the recording I've just done
- 9:38and lip-s sync that with an invented AI
- 9:41character to get some really cool
- 9:43results. That is just a few of the many
- 9:46ways you can use the 11 Labs creative
- 9:49platform.
- 9:50>> And now you know how to create AI
- 9:52avatars with 11 Labs that look and sound
- 9:54100% like you. If you have any
- 9:56questions, let us know in the comment
- 9:57section down below. And if you enjoyed
- 9:59this video, please hit that like button
- 10:00and don't forget to subscribe. Thanks
- 10:02for watching.
About this transcript
This page contains the full transcript of Create Custom Realistic AI Avatars That Look & Sound 100% Like You (Full Workflow) by ElevenLabs, generated from the public captions YouTube serves with the video. The transcript has 2,333 words across 314 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.
What you can do with it
Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to choose a caption track available on the video.
Free YouTube transcript tool
YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, caption language selection, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.