flowdrop_ai_provider
The FlowDrop AI Provider module brings powerful multimodal AI capabilities to FlowDrop workflows by integrating seamlessly with the Drupal AI ecosystem.
It enables content creators and site builders to embed AI-driven chat, text, image, audio, video, translation, embedding, and moderation capabilities directly into FlowDrop pipelines with no additional configuration.
Key Features
- AI Provider Integration
- AI Prompts
- AI Guardrails
- Chat
- Embeddings
- TextToImage
- ImageToImage
- ImageToVideo
- ImageAndAudioToVideo
- ImageClassification
- TextToSpeech
- SpeechToSpeech
- AutoToAudio
- TranslateText
- Moderation
- Zero-Config Setup
Connects FlowDrop workflows with any provider supported by the Drupal AI module, enabling flexible AI model selection including local models, cloud APIs, and open-source LLMs.
Leverages the Drupal AI Prompt system to define reusable, structured prompts for AI interactions inside FlowDrop pipelines. Prompts can include dynamic variables, contextual data from workflow inputs, and templated instructions to ensure consistent and controllable AI behavior across automated processes.
Integrates with Drupal AI Guardrails to enforce safety, validation, and content policies within FlowDrop workflows. Guardrails allow developers and site builders to apply moderation rules, output validation, and safety constraints to AI responses before they are passed to the next workflow step.
Execute AI chat requests directly within FlowDrop nodes. Supports multi-turn conversations, structured prompts, streaming responses, and advanced configuration inherited from Drupal AI and AI Agents.
Generate vector embeddings for content indexing, semantic search, similarity comparison, and AI-powered content discovery workflows.
Create AI-generated images from text prompts inside FlowDrop pipelines, enabling dynamic media generation and creative automation.
Transform and enhance existing images using AI-driven style transfer, editing, variation generation, and refinement workflows.
Convert static images into dynamic AI-generated video sequences for engaging multimedia experiences.
Generate synchronized videos by combining image inputs with audio tracks, enabling automated video production workflows.
Analyze and classify images to automatically tag, categorize, and moderate visual content within FlowDrop processes.
Convert text into natural-sounding speech for voice-enabled experiences, accessibility enhancements, and automated narration.
Transform spoken input into AI-processed speech output, enabling real-time voice interactions and conversational workflows.
Automatically process and transform audio inputs for AI-driven analysis, enhancement, or content generation within FlowDrop pipelines.
Translate text between multiple languages using AI-powered translation models, enabling multilingual content automation.
Detect and filter unsafe or inappropriate content using AI moderation models to maintain content quality and compliance.
Ships with ready-to-use AI model configurations. After installation, FlowDrop automatically gains new AI-powered processors with no manual configuration required.