Captions offers Foundation Models
Product
Foundation Models are Mirage's multimodal audio and video models that generate realistic talking videos from text, audio, or images.
- Currently Offered
Foundation Models are Mirage's multimodal audio and video models that generate realistic talking videos from text, audio, or images.
Foundation Models are Mirage's in-house trained audio and video foundation models designed for short-form, UGC-style content. The models generate realistic A-roll footage with natural lip movement, eye contact, gestures, and emotional expression from inputs such as scripts, audio files, or reference images.
The model family includes Mirage video and Mirage audio, trained on licensed datasets and served through Mirage Studio, the Captions app, and the Mirage API for creators, marketers, and developers.
Full-duplex audiovisual foundation model for real-time face-to-face AI conversation.
Runway API gives developers access to Runway's generative video, image and audio models.
AI avatar video platform that generates presenter-style videos from a cloned likeness and voice.
LTX Models is Lightricks' family of generative video and audio models for developers and enterprises.
Runway Characters creates real-time conversational video agents from a single image.
AI video generation and creative platform built on generative world models.
Full-duplex audiovisual foundation model for real-time face-to-face AI conversation.
Runway API gives developers access to Runway's generative video, image and audio models.
Luma Dream Machine is an AI video generation product that creates cinematic clips from text and images.
AI voice generation platform for text-to-speech voiceovers, voice agents, and AI dubbing.
Stable Audio generates music and sound effects from text for creative production workflows.
Creative AI platform for generating and localizing speech, music, images, and video.
Foundation models and AI agents for spatial-temporal reasoning in virtual and physical environments.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Marengo is TwelveLabs' multimodal video embedding model for semantic search, classification, and understanding across video, image, and audio.
AI avatar video platform that generates presenter-style videos from a cloned likeness and voice.
LTX Models is Lightricks' family of generative video and audio models for developers and enterprises.
AI super agent platform unifying chat, image, video, and voice generation.
Runway Characters creates real-time conversational video agents from a single image.
AI video generation and creative platform built on generative world models.
Luma Dream Machine is an AI video generation product that creates cinematic clips from text and images.
AI voice generation platform for text-to-speech voiceovers, voice agents, and AI dubbing.
Stable Audio generates music and sound effects from text for creative production workflows.
Creative AI platform for generating and localizing speech, music, images, and video.
Runway Gen-4.5 is a state-of-the-art AI video generation model for cinematic text-to-video and image-to-video creation.
Foundation models and AI agents for spatial-temporal reasoning in virtual and physical environments.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Marengo is TwelveLabs' multimodal video embedding model for semantic search, classification, and understanding across video, image, and audio.
