Start creating

MeiGen

InfiniteTalkAI talking avatar generator

A talking video at 480p from a photo and your text, as long as the line: up to about 8 seconds. A run takes about 5 to 10 minutes. On Leap, it sits beside 174 other models in one studio.

  • Talking avatar

Your words wait while you sign in.

  • No subscription
  • Every top model, one account
  • Pay per run, priced before it starts
A nurse's night shift, in one line, a real run on Leap
A nurse's night shift, in one line

AI talking avatar generator

InfiniteTalk at a glance

InfiniteTalk is a talking avatar model from MeiGen. It makes video from words, words or a first frame.

Made by
MeiGen
Makes
Video
Starts from
Words, words or a first frame
Voices
20 to choose from
Prompt
Up to 4,000 characters
Price
$13.50 per 1,000 characters
Updated
October 4, 2026
  1. 01Describe what you want to see
  2. 02See the exact price, then press go
  3. 03Keep it in your library, or take it further

Side by side

More video models on Leap

No prompt needed

Or start from a recipe

Recipes write the prompt for you: add a photo, pick a look, and get a finished result.

Every recipe

Why Leap

Why creators make it on Leap

  1. 01

    Every top model, side by side

    175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.

    See the models
  2. 02

    One click, or full control

    Character Studio, effects and recipes write the prompt for you. Or write your own for any model.

    See the tools
  3. 03

    Your work stays yours

    Everything you make stays in your library while your account is active, and you own what you make here.

    See what people make
  4. 04

    One balance for everything

    The studio, the API and your agents spend the same balance, and every run shows its price before it starts.

    How pricing works

Questions

InfiniteTalk, answered

What is InfiniteTalk?
InfiniteTalk is a talking avatar model from MeiGen. A talking video at 480p from a photo and your text, as long as the line: up to about 8 seconds. A run takes about 5 to 10 minutes. It is new on Leap and in preview: it works, and it may still change. On Leap it runs in one studio beside every other top model, with one account.
Can InfiniteTalk start from a photo?
Yes. InfiniteTalk starts from words, words or a first frame. The photo becomes the first frame, cropped to the video's shape.
Which voices can I use?
20 voices, among them Aria, Roger, Sarah, Laura and Charlie. You can hear each one in the studio before you run it.
How much does a run cost?
It costs $13.50 per 1,000 characters. You see the exact price before you press go, and a run that fails costs nothing.
Is InfiniteTalk free to try?
No. There is no free credit: you add credit from $5, and your first top-up has no card fee. It costs $13.50 per 1,000 characters. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?
Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?
Yes. Leap's REST API runs it as meigen/infinitalk, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need a MeiGen account?
No. Leap sends your request to MeiGen's model and gives you what it makes. One Leap account runs InfiniteTalk and every other model, in the studio, through the API and from your agents.

Your idea, InfiniteTalk.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with InfiniteTalk

For developers

Run InfiniteTalk from code

API docs
Model ID
meigen/infinitalk
Makes
Video
Pricing
Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Texttext
Text, up to 160 characters, required
Promptprompt
Text, up to 4,000 characters, required
First framefirst_frame
An image, requiredAn image the video starts from. It is cropped to the video's shape.
Voicevoice
Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill. Default: Aria
Accelerationsettings.acceleration
None, Regular, High. Default: RegularThe acceleration level to use for generation.
Seedseed
0 to 4294967295The same seed and input give the same image.

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. A file input takes the ID that POST /v1/files returns for your upload. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "meigen/infinitalk",    "input": {      "first_frame": "file_...",      "text": "A paper boat drifting down a rainy street at dusk",      "prompt": "A paper boat drifting down a rainy street at dusk"    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"