---
title: "MeiGen-AI AI models — API access via RunAPI"
url: "https://runapi.ai/providers/meigen-ai.md"
canonical: "https://runapi.ai/providers/meigen-ai.md"
locale: "en"
provider: "MeiGen-AI"
line_count: 1
variant_count: 0
---

# MeiGen-AI

InfiniteTalk — audio-driven talking-head animation with lip-sync from portrait images.

MeiGen-AI develops InfiniteTalk, an audio-driven talking-head model that generates lip-synced animated video from a portrait image and any audio input, supporting unlimited-length output.

## Models

- [InfiniteTalk](https://runapi.ai/models/infinitetalk.md) — Video, 1 endpoints · from $0.120

## Variants

No separate variant URLs. Single-SKU lines are documented on their model page.

## Install

```sh
npm install @runapi.ai/<line>
```

## FAQ

### Is this an official %{provider} integration?

RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.

### Do I need a %{provider} account?

No — your RunAPI key is enough for managed access.

### What&#39;s the latency overhead from proxying?

Typically under 20 ms. RunAPI keeps the proxy layer close to model execution regions.

### Are images / videos cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I bring my own key?

Not currently — calls use RunAPI-managed access.