Creative & media
Generative tools for producing and editing visual, audio, and video content, from design canvases to image, video, and music models.
Design and creative
Generative design canvases that turn prompts into editable visuals, prototypes, and production assets.
- Claude Design - Anthropic Labs tool that turns prompts into designs, prototypes, slides, and decks and can apply your team's design system.
- Krea - Real-time generative canvas for image, video, and 3D creation.
- Pencil - AI-native design canvas for developers that generates editable designs and production-ready code from a VS Code or Cursor integration.
- Photoroom - AI photo editor and product-image studio with instant background removal and generative editing.
- Weavy - Node-based creative canvas that chains AI models for image, video, and 3D generation and editing.
Image generation
Text-to-image models and editors for creating and refining still images.
- Flux - Black Forest Labs' open-weight and hosted models known for photoreal prompt adherence.
- Imagen - Google DeepMind's text-to-image model generating high-resolution images with SynthID watermarking.
- Magnific - AI upscaler and enhancer that adds detail and reimagines images at high resolution.
- Midjourney - Generative image service known for a consistent aesthetic and a large creator community.
- Nano Banana - Google's Gemini-based image model line known for precise, conversational editing.
- Seelab - AI photo studio that trains custom models on your products and brand to generate on-brand product visuals.
Video generation
Models and studios that generate and edit video, some with natively synchronized audio.
- Google Flow - AI filmmaking studio built on Veo and Imagen for generating and editing cinematic scenes.
- HeyGen - Generates talking-avatar videos from a script, with voice cloning and translation for marketing and training.
- Kling - Kuaishou's video model with long-duration generations and strong motion coherence.
- Pika - Generative video app with effects-driven editing and social sharing.
- Runway - Video model suite and editor used in film and advertising production.
- Veo - Google DeepMind's video model producing high-resolution clips with natively generated synchronized audio.
Audio and music
Speech-to-text, text-to-speech, voice cloning, and full music generation.
- AssemblyAI - Speech-to-text and audio-intelligence API with transcription, diarization, and LLM-powered audio understanding.
- Deepgram - Voice AI API for fast, accurate speech-to-text and text-to-speech built for real-time agents.
- ElevenLabs - Voice synthesis platform covering cloning, dubbing, conversational agents, and audiobooks.
- Gladia - Audio infrastructure API for real-time and async speech-to-text, diarization, and translation across 100+ languages.
- Gradium - Kyutai spinout building ultra-low-latency text-to-speech, speech-to-text, and voice-cloning models for voice agents, behind a single API.
- Suno - Text-to-song model that generates full vocal tracks from a prompt.
- Udio - Music generation model with fine control over style and structure.