Skip to main content
skill CX Codex

alibabacloud-avatar-video — Claude Code skill

alibabacloud-avatar-video is a Claude Code skill for creating talking-head videos, full-body animations, and speech via Alibaba Cloud DashScope. It supports portrait animation, character motion, and text-to-speech with voice selection.

no license 125 installs ★ 300 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a claude-code
Open on GitHub

What alibabacloud-avatar-video does

Seven built-in tools are included: LivePortrait converts a portrait photo and audio into talking-head video in two steps; EMO offers another method to animate a portrait with speech; AnimateAnyone handles full-body motion based on motion templates; T2I generates images from text prompts using Wan 2.x; I2V turns images into video, supporting text-to-image-to-video pipelines; Qwen TTS synthesizes speech with voice and tone selection by scenario; LingMou creates digital-human broadcast videos from pre-built templates.

You need Alibaba Cloud credentials (DASHSCOPE_API_KEY, OSS access keys), ffmpeg and ffprobe in PATH, and environment variables for your bucket and endpoint. Beijing and Singapore region API keys are not interchangeable—use the key for your region.

Each tool runs as a separate script in the scripts folder: live_portrait.py, qwen_tts.py, text_to_image.py, and more. Flags let you choose model, size, voice, and style; outputs save to Object Storage or download locally.

What it helps with

  • generate a talking-head video from a photograph and audio track
  • synthesize speech from text with voice and tone options
  • create an image from a text description
  • animate a character with full-body motion from a template
  • produce a character video from an image and text in one call

Example prompts for the agent

  • Turn a portrait photo into talking video: use LivePortrait with --template active for expressive motion
  • Convert a speech transcript to audio with a news anchor voice using --scene news
  • Generate a video of a character in traditional clothing from a text prompt—first text to image, then image to video

How to install alibabacloud-avatar-video

1Skills CLI (Vercel)

npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a claude-code

2Manually: put the files in place

~/.claude/skills/alibabacloud-avatar-video/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/alibabacloud-avatar-video/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about alibabacloud-avatar-video

How do I install alibabacloud-avatar-video in Claude Code?

Run npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a claude-code, then open the configuration file at ~/.claude/skills/alibabacloud-avatar-video/SKILL.md. The skill will then be ready to use.

What does alibabacloud-avatar-video do?

It generates video and audio via Alibaba Cloud APIs. You can animate a photo with synthesized speech, create images from text descriptions, turn images into video, animate characters with full-body motion, or produce digital-human template videos.

What API keys do I need?

You need DASHSCOPE_API_KEY for the Beijing region (cn-beijing), along with ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET for Object Storage Service access. Also set OSS_BUCKET and OSS_ENDPOINT environment variables. Note that Beijing and Singapore region keys only work in their respective regions.

Similar skills

All skills for AI and ML →

From the same set66

The whole set →
alibabacloud-sms-send-short-message The alibabacloud-sms-send-short-message skill sends Alibaba Cloud SMS for verification codes, alerts, reminders, and campaigns. It covers single and per-recipient batch delivery. CX Codex +1 133installs alibabacloud-cfw-internet-firewall-protect alibabacloud-cfw-internet-firewall-protect is a skill that checks public-IP protection in Alibaba Cloud Cloud Firewall and changes settings for selected resources. CX Codex +1 129installs alibabacloud-maxcompute-migration-service alibabacloud-maxcompute-migration-service orchestrates data migration to Alibaba Cloud MaxCompute via MMS. Handles metadata scanning, schema mapping, and Spark execution monitoring. CX Codex +1 127installs alibabacloud-elasticsearch-instance-diagnose alibabacloud-elasticsearch-instance-diagnose — a skill for analyzing Elasticsearch cluster health on Alibaba Cloud. Collects data from OpenAPI and REST API, identifies root causes of failures, and suggests remediation steps. CX Codex +1 127installs alibabacloud-emas-apm-query alibabacloud-emas-apm-query investigates mobile app issues in Alibaba Cloud EMAS APM, then matches sample stacks to project code to suggest fixes. CX Codex +1 112installs alibabacloud-agentbay-aio-skills alibabacloud-agentbay-aio-skills executes Python, JavaScript, R, and Java code in an isolated AgentBay cloud sandbox instead of your local machine. Useful for data analysis and plotting. CX Codex +1 112installs alibabacloud-sas-multiaccount-manage The alibabacloud-sas-multiaccount-manage Claude Code skill manages Alibaba Cloud accounts and exports Security Center reports. It combines enabled accounts’ results into an Excel workbook. CX Codex +1 112installs alibabacloud-sls-data-agent alibabacloud-sls-data-agent — a skill for Claude Code connects SLS DataAgent to Alibaba Cloud Simple Log Service. Turns plain-language queries into log analysis, aggregations, and dashboard summaries. CX Codex +1 111installs

Project sponsors

Companies that keep this analytics open