Avatar v2 · guided call

A 5-minute
call makes
the avatar.

Your user talks to Lily, an AI host under your brand. Nothing to film or upload. You get their avatar, their voice and what she learned about them, over the API.

Free account, no card. The call uses 30 of your 60 free tokens.

Your brand02:14
Lily
What do your followers ask you most?
Example screen. Your logo, your colours, your name for the host.

One call in. Everything out.

What comes back on the avatar object. The examples below are illustrative.

video_urlpreview_image_url

The avatar and a photo

Cut from the best stretch of the call. 1:1 the person, ready for POST /generations.

av_amara
voice_sample_urlclips[]

Their voice and their moods

Up to five minutes of clean speech for cloning, and clips by emotion you can pick per phrase.

1:042:41 of clean speech
smiledriveserioussadsurpriselisten
profiletranscript[]

What Lily learned about them

Plain text, shaped by your brief. Paste it into your prompts and every script sounds like the person.

Amara makes skincare content and sells her own serum. She films UGC-style ads for her store.

Audience:
women 25–40 who are tired of 10-step routines
What sells:
one product, visible result in two weeks, before/after in the first 3 seconds
How she talks:
fast, first person, “okay, real talk”, never says “glow”
Also:
launching a body line in spring
You tell Lily what your tool needs
POST /api/v1/capture_sessions
{
  "context": "We generate UGC-style video ads for creators' own products.",
  "goal": "Who buys from them, what sells, how they talk on camera.",
  "language": "en",
  "branding": { "name": "Your brand", "assistant_name": "Lily" }
}

# 201 → a link for your user
She asks, listens and follows up
  • LilyWhat do your followers ask you most?
  • AmaraHonestly? Whether it works on sensitive skin. Every single day.
  • LilyAnd what do you tell them?

Three steps. None of them is filming.

  1. 1

    You create a session

    One request with what your product does and what to find out. You get a link, or run the call inside your own UI with our JS SDK.

  2. 2

    Your user talks to Lily

    About five minutes on a laptop or phone. She interviews them by voice, follows up, and asks for a smile or a serious take if it didn't come up.

  3. 3

    You get the avatar

    A webhook with the photo and profile seconds after the call, then the finished avatar a few minutes later. Same avatar_id as any other.

30 tokens per avatar, charged only when the call is finished. English and Russian today. Clip upload vs call

Take the call
your users will take.

Sign up, talk to Lily for five minutes and get your own avatar. The tokens you have left make your first video.

You'll need a camera and a microphone. Laptop or phone.

A 5-Minute AI Call That Makes the Avatar — PitchTwin