avatarInteractive AI avatar with Simli video rendering and ElevenLabs TTS
Install via ClawdBot CLI:
clawdbot install Johannes-Berggren/avatarInteractive AI avatar interface for OpenClaw with real-time lip-synced video and text-to-speech.
export SIMLI_API_KEY=your-key
export ELEVENLABS_API_KEY=your-key
openclaw-avatar
When responding to avatar queries, use this format:
<spoken>
A short conversational summary (1-3 sentences). NO markdown, NO formatting. Plain speech only.
</spoken>
<detail>
Full detailed response with markdown formatting (bullet points, headers, bold, etc).
</detail>
User: "What meetings do I have today?"
<spoken>
You have three meetings today. Your first one is a team standup at 9 AM, then a product review at 2 PM, and finally a 1-on-1 with Sarah at 4 PM.
</spoken>
<detail>
## Today's Meetings
### 9:00 AM - Team Standup
- **Duration**: 15 minutes
- **Attendees**: Engineering team
### 2:00 PM - Product Review
- **Duration**: 1 hour
- **Attendees**: Product, Design, Engineering leads
### 4:00 PM - 1:1 with Sarah
- **Duration**: 30 minutes
- **Notes**: Follow up on project timeline
</detail>
Avatar responses use session key: agent:main:avatar
Generated Mar 1, 2026
Deploy the avatar as an interactive customer service representative on e-commerce websites, providing spoken responses to common queries while displaying detailed product information or troubleshooting steps. This enhances user engagement and reduces live agent workload by handling routine inquiries with a human-like interface.
Use the avatar to deliver training modules with spoken summaries and detailed markdown content for onboarding or compliance programs. It can simulate realistic interactions, making learning more engaging and accessible across multiple languages for global teams.
Implement the avatar in hospital waiting areas or clinics to explain medical procedures, provide health tips, and answer FAQs with clear spoken guidance and detailed visual information. This improves patient communication and reduces staff burden in high-traffic environments.
Integrate the avatar into property listing websites to offer spoken overviews of homes and neighborhoods, while displaying detailed markdown with pricing, amenities, and contact info. This creates an immersive experience for potential buyers, boosting engagement and lead generation.
Deploy the avatar on banking or investment platforms to explain financial products, summarize account details, and provide investment tips with conversational speech and structured markdown data. It helps demystify complex information for clients, enhancing trust and accessibility.
Offer the avatar as a cloud-based service with tiered pricing based on usage, API calls, or features like multi-language support and Slack integration. This generates recurring revenue from businesses seeking scalable, interactive AI interfaces without heavy upfront development costs.
Sell custom licenses to large organizations for on-premise deployment, including dedicated support, customization, and integration with existing systems like CRM or training platforms. This targets industries with high security or compliance needs, ensuring steady high-value contracts.
Provide a free basic version with limited API calls or features, then monetize through premium add-ons like advanced avatar customization, additional TTS voices, or enhanced analytics. This attracts small businesses and developers, converting them to paid plans as needs grow.
💬 Integration Tip
Ensure API keys are securely stored and test the avatar locally before deployment to avoid service disruptions; use the provided response format to align spoken and detailed content effectively.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.