InfiniteTalk API Skill for RunAPI

Install this agent skill, inspect InfiniteTalk fields, then run jobs through the RunAPI CLI.

Model Reference · CLI · SDK

Generate lip-sync video from audio and a portrait image with InfiniteTalk. This skill helps Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents integrate InfiniteTalk through RunAPI.

The canonical agent file is skills/infinitetalk/SKILL.md.

Install

npx skills add runapi-ai/infinitetalk -g

Or paste this prompt to your AI agent:

Install the infinitetalk skill for me:

1. Clone https://github.com/runapi-ai/infinitetalk
2. Copy the skills/infinitetalk/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

Quick example

import { InfinitetalkClient } from '@runapi.ai/infinitetalk';

const client = new InfinitetalkClient();
const result = await client.audioToVideo.run({
  model: 'infinitetalk-from-audio',
  image_url: 'https://cdn.example.com/portrait.jpg',
  audio_url: 'https://cdn.example.com/speech.mp3',
});
const url = result.videos[0].url;

Routing

• Model page: https://runapi.ai/models/infinitetalk
• Product docs: https://runapi.ai/docs#infinitetalk
• SDK docs: https://runapi.ai/docs#sdk-infinitetalk
• SDK repository: https://github.com/runapi-ai/infinitetalk-sdk
• Pricing and rate limits: https://runapi.ai/models/infinitetalk
• Provider comparison: https://runapi.ai/providers/meigen-ai
• Browse all RunAPI models and skills: https://runapi.ai/models

Agent rules

• Keep API keys in RUNAPI_API_KEY or RunAPI CLI config; never commit secrets.
• Prefer create, get, and run JSON passthrough patterns instead of inventing flags for every model parameter.
• For infinitetalk api pricing, rate-limit, and commercial-usage answers, link to the model page rather than the repository README.

License

Licensed under the Apache License, Version 2.0.