InfiniteTalk

by anbeime

InfiniteTalk is an Automation skill for Claude Code, published by anbeime in skill.

5.3K stars519 forkson anbeime/skillAdded 2026/08/16+3% in starsRepository updated 2026/08/16

View source on GitHub Download repo ZIP

claude-skillsfinance-skillgemini-skillshermes-skilloffice-skillopenclaw-skillsskillskill-mdskills

Install in seconds

Install InfiniteTalk

Copy InfiniteTalk into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/anbeime/skill/tree/main/skills/infinitetalk ~/.claude/skills/infinitetalk

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/anbeime/skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/infinitetalk/SKILL.md in anbeime/skill
Installs to: ~/.claude/skills/infinitetalk
Collection: One of 23 skills cataloged from this repository
Category: Automation — 1523 skills

What InfiniteTalk does

InfiniteTalk generates audio-driven talking head videos from a single image or existing video, with synchronized lip, head, and body motion. Use it to create digital human videos, dub videos, or produce virtual streamer content, supporting unlimited duration and low-memory optimization.

InfiniteTalk is cataloged under Automation on DirSkills. InfiniteTalk comes from a repository tagged claude-skills, finance-skill, gemini-skills, hermes-skill and office-skill.

Documentation

README

Excerpt

InfiniteTalk - 音频驱动视频生成

任务目标

本 Skill 用于：将音频（语音）转换为同步的说话人视频，支持从单张图片或现有视频生成音频驱动的说话视频
能力包含：
- Image-to-Video：从单张图片生成音频驱动的说话视频
- Video-to-Video：对现有视频进行音频驱动的重配音
- 多维度同步：唇形、头部运动、身体姿态、面部表情与音频精准对齐
- 无限时长：支持无限制时长的视频生成
- 低显存适配：支持量化、模型卸载等显存优化方案
触发条件：当需要生成音频驱动的数字人视频、视频配音、虚拟主播内容时使用

前置准备

模型下载：在使用本 Skill 前，必须先下载所需的模型权重文件，具体步骤见 references/model_download.md
硬件要求：
- GPU：推荐使用 16GB+ 显存的 GPU（可使用量化方案适配低显存设备）
- 内存：建议 32GB+ 系统内存
- 磁盘空间：至少 50GB 可用空间（模型权重约 30GB）
环境配置：详细依赖安装见 references/environment_setup.md

操作步骤

模式一：Image-to-Video（图片生成视频）

准备输入
- 确保有一张清晰的人脸图片作为输入
- 准备音频文件（支持 mp3、wav 等格式）
- 可选：使用 TTS 功能从文本生成音频

This is the opening of the README. Read the full README on GitHub.

Frequently asked about InfiniteTalk

What else does anbeime publish alongside InfiniteTalk?
InfiniteTalk is one of 23 skills that DirSkills catalogs from anbeime/skill, the repository it ships in. Its siblings there include Agent Team, AgentKit Multimedia Shopping and Antinet Doc Parse. Each one is a separate skill with its own page in this directory, installs the same way InfiniteTalk does, and is maintained by anbeime in that same repository. The rest of the collection is listed on the anbeime/skill page.
How does InfiniteTalk compare to other Automation skills?
InfiniteTalk ranks #274 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of InfiniteTalk against them. Open each page to compare what they document and how they install.