A specialized tool for Openclaw Skills that converts text or audio into animated circular avatar videos with automated lip-sync and blink cycles.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install talking-circle
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install talking-circle using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Talking Circle AI Video Generator?
The Talking Circle skill provides a robust framework for creating animated circular avatar videos, commonly used for Telegram-style video messages. By processing a set of four static character frames—neutral, slight open, wide open, and blinking—the skill dynamically generates a video where the character's mouth movements sync perfectly with the audio amplitude. This functionality is a key asset within the Openclaw Skills ecosystem for users looking to automate character-based video content without manual animation.
Built for performance and ease of use, it utilizes Python and FFmpeg to apply professional circular masking and smooth frame transitions. Whether generating speech from text via integrated providers or using pre-recorded audio, this addition to Openclaw Skills enables high-quality, character-driven communication at scale.
Talking Circle AI Video Generator Use Cases
- Creating automated Telegram-style round video messages for customer support bots using Openclaw Skills.
- Generating character-driven educational or news snippets from simple text inputs.
- Producing personalized video greetings for marketing campaigns with consistent character branding.
- Enhancing AI assistant responses with visual, animated avatar feedback.
How Talking Circle AI Video Generator Works
- The user provides an audio file or text input which is processed by the Openclaw Skills logic to generate a speech waveform.
- The system analyzes the Root Mean Square (RMS) amplitude of the audio to determine the appropriate mouth state for every frame.
- A frame sequence is constructed by mapping amplitude thresholds to three mouth positions (closed, slightly open, wide open).
- An independent blink loop is overlaid on the sequence to simulate natural character movement.
- FFmpeg merges the generated frame sequence with the audio and applies a circular alpha mask for the final output.
Talking Circle AI Video Generator Setup
Prerequisites
Before using this skill in your Openclaw Skills setup, ensure python3 (3.9+) and ffmpeg are installed and accessible in your system PATH.
Manual Installation
While most Openclaw Skills handle dependencies automatically, you can install the requirements manually:
pip install -r requirements.txt
API Configuration
To enable text-to-video features, configure your preferred TTS provider:
# For ElevenLabs
export ELEVENLABS_API_KEY='your_api_key'
# For SaluteSpeech (Sber)
export SALUTE_SPEECH_AUTH='your_base64_credentials'
Talking Circle AI Video Generator Data Schema & Taxonomy
The skill manages data through a 4-frame image architecture and standard video exports.
| Data Component | Type | Requirement |
|---|---|---|
neutral.png |
Image | Mouth closed, eyes open |
slight.png |
Image | Mouth slightly open, eyes open |
wide.png |
Image | Mouth wide open, eyes open |
blink.png |
Image | Mouth closed, eyes closed |
output.mp4 |
Video | 720x720 (640px circle diameter) |
All input frames must have identical resolutions and positioning to ensure visual consistency across the Openclaw Skills output.
Talking Circle AI Video Generator Advanced Features
- Support for multiple TTS engines including ElevenLabs and SaluteSpeech (Sber) for multi-language video generation.
- Adjustable amplitude thresholds (
--amp-low,--amp-high) for precision lip-syncing across different audio qualities. - Customizable blink timing parameters allowing users to define start delay and frequency of eye movements.
- Seamless integration with external audio sources, making it compatible with OpenAI TTS or local voice models within the Openclaw Skills environment.
- Automated workflow guidance for using AI image generation to create perfectly aligned character frames.
SKILL.md
Loading
Related Openclaw Skills
Telegram Inline Buttons
A specialized skill for implementing interactive inline keyboards in Telegram to streamline agent-to-human decision-making and confirmations.
Self-Improvement Skill
A systematic framework for AI agents to log errors, user corrections, and new insights to enable continuous self-optimization.
Text Detection Skills
A comprehensive suite of forensic tools for identifying AI-generated text through advanced NLP, pattern analysis, and machine learning classification.
Smart Cache
A high-performance caching utility providing intelligent data retention through LRU and LFU eviction strategies.
Bilibili Video Analyzer
An automated tool for converting Bilibili educational content into structured, clean-style study notes with AI-driven insights and visual aids.
calctl
A command-line interface for macOS that provides high-speed access to Apple Calendar events using icalBuddy and AppleScript.
Featured*
