send-video-message

Generate lip-synced AI avatar videos from text via the Runway Character API.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/runwayml/openclaw-skill-send-video-message --skill send-video-message
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: send-video-message
Source: https://github.com/runwayml/openclaw-skill-send-video-message/tree/main
Command: npx skills add https://github.com/runwayml/openclaw-skill-send-video-message --skill send-video-message

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires runwayml, httpx, and includes scripts (resource) components.

What problem does it solve?

Receives a text input and returns a video message featuring a lip-synced AI avatar, enabling clearer, face-to-face-style communication in chat.

Core Features & Use Cases

  • Lip-synced video generation from plain text using Runway Character API.
  • Support for custom avatars via saved avatar IDs or predefined presets, including one-time avatar setup.
  • Ideal for async updates, code reviews, incident summaries, and status briefings where a video explains context more effectively than text.

Quick Start

Provide the text you want spoken to generate and deliver a lip-synced video message.

Frequently Asked Questions about send-video-message

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a lip-synced AI avatar video from text?

To generate a lip-synced AI avatar video from text, you provide plain text input to the Skill, which then uses the Runway Character API to synthesize and deliver the video message automatically.

Do I need a Runway API key to create text-to-speech avatar videos?

Yes, you need a Runway API key configured as RUNWAY_API_SECRET to authenticate requests and generate text-to-speech avatar videos through the Runway Character API.

Can I use a custom avatar for my async video updates?

Yes, you can use a custom avatar for async video updates by configuring a saved avatar ID or selecting predefined presets during the one-time avatar setup process.

What is the best way to deliver incident summaries or code reviews via video?

The best way to deliver incident summaries or code reviews via video is using automated lip-synced AI avatars, which convey facial context more clearly than plain text for asynchronous communication.

What format does the lip-synced video message output use?

The lip-synced video message outputs a downloadable video file accompanied by a MEDIA tag, ensuring the generated content is easily accessible and shareable within your communication pipeline.

Does the avatar video generation process handle error states?

Yes, the avatar video generation process handles error states internally, managing avatar setup and potential API failures to ensure reliable video message delivery from your text input.