How do I build my avatar — from a photo or by generating one?
Your Podcast Studio avatar can start from either a photo or a written description — whichever you have on hand. Both paths lead to exactly the same result: an avatar composed and baked into your chosen studio environment, ready to speak your lines. Neither is the "better" option; it's purely a matter of what you'd rather do.
Before you start
If this is your first time in Podcast Studio, you'll be asked to confirm your photo is of you (or you have rights to use it) and any voice you record is your own. See What is Podcast Studio? for details — it only appears once.
Choosing your path
At the top of the "Your avatar" panel, on the Avatar tab, you'll see two options: Upload photo and Generate. Pick either one — you can switch between them freely until you've actually approved an avatar.
Option A — Upload a photo
- Click Upload photo, then choose a file (or drag one in).
- A preview of your photo appears, along with a name field.
- Enter your display name.
- Click Build my avatar.
A clear, front-facing photo with good lighting gives the best result — the same way it would for any headshot.
Option B — Generate from a description
- Click Generate.
- Enter your display name.
- Describe your look — hair, build, style, what you're wearing works best. For example: "A tall woman in her 30s with natural locs, warm smile, wearing a navy blazer."
- Click Generate. A preview appears in a few moments.
- Looks right? Click Use this. Not quite it? Click Regenerate and try again.
You get 3 generations per avatar. Every attempt counts against that total, including ones that don't come out right. Each preview shows how many you have left. If you run out, you can switch to Upload photo and finish that way instead — nothing is lost.
Describe physical features and style rather than naming a specific real person — descriptions that read as a real, identifiable individual won't generate. See Why was my avatar generation rejected? if this happens to you.
Approve and bake
Whichever path you took, the moment you click Build my avatar (photo) or Use this (generated preview), the same thing happens: AwakeVerse composes your avatar and bakes it into your chosen studio environment. A progress view shows each stage — composing, then baking — and finishes with your avatar ready to use. This takes a similar amount of time either way, and produces the same quality of result.
What happens after
Your finished avatar appears in your saved avatars for this session, and:
- If you're building a solo voice podcast, it's your narrator.
- If you're building an open conversation, it becomes the host, and you'll add a guest avatar alongside it — see How do I add a guest to my podcast?
From here, move on to picking your environment — see How do I choose a studio environment for my podcast?
What AwakeVerse handles for you
- One build pipeline for both paths — a generated avatar and a photo avatar go through identical composing and baking, so there's no difference in how they look or behave later on.
- Content safety checks on every generated preview, run automatically.
- Your saved avatars, kept around — built avatars stay available so you can reuse or swap between them; see How do I switch or rebuild my avatar?
When it's done
Your avatar is ready — same next steps regardless of which path you took: choose your environment, add a guest if you're doing an open conversation, and move on to your script.
Also worth a click
- Why was my avatar generation rejected?
- How do I switch or rebuild my avatar?
- How do I choose a studio environment for my podcast?
Related: What is Podcast Studio? · Why was my avatar generation rejected? · How do I add a guest to my podcast?