← Back to ChatStudio

ChatStudio Help

💬 Chat Interface

Chat with AI models using a modern interface. Select models, manage conversations, and customize settings.

Features

📎 File Attachments

Attach files to your messages using the paperclip button. Supported formats:

Images: PNG, JPG, GIF, WEBP, SVG
Documents: PDF (with text extraction)
Code: JS, TS, HTML, CSS, JSON, PY, MD, TXT, XML, YAML

🎤 Voice Input

Use the microphone button to speak your message. The Speech Recognition API converts your voice to text in real-time.

Tips: Speak clearly and pause between sentences. Click the microphone again or press Enter to send.

📄 PDF Preview

When you attach a PDF, click the preview icon to:

View the PDF inline
Extract and copy text
Edit extracted text before sending

🔗 URL Previews

When you paste a URL, ChatStudio automatically fetches a preview with title, description, and favicon.

💻 Code Highlighting

Code blocks are syntax-highlighted in a sandboxed iframe for security. Use markdown formatting:

```javascript
console.log('Hello, World!');
```

Models

Choose from various AI models including:

Cloud Models: qwen3.5, gemma3, deepseek-r1
Coder Models: qwen2.5-coder, deepseek-coder
Vision Models: llava, moondream (for image analysis)

Keyboard Shortcuts

Enter - Send message
Shift + Enter - New line in input
Ctrl + K - Clear conversation (if implemented)

Privacy

All conversations are stored locally in your browser. No data is sent to external servers except for AI processing through the configured API endpoint.

Troubleshooting

Model Timeout

If a model times out, try a smaller cloud model like qwen3.5:7b instead of larger models.

Voice Not Working

Make sure your browser supports the Web Speech API and has microphone permissions enabled.

File Upload Issues

Ensure file sizes are reasonable. Large PDFs may take longer to process.