CraftStory Model 2.0 is a talking-photo video model driven by a photo and a driving video, animating a single image into a talking video up to 30 minutes long, with the photo locking the character's identity and the driving video setting the motion. The model captures subtle facial expressions, hand gestures, and emotional cues. Movement intensity, pacing, and eye focus are adjustable.
CraftStory Model 2.0 keeps visual consistency across long sequences rather than only short clips. Audio can be uploaded or generated from a script with lip movements synced to the voice, and the model supports landscape and portrait formats at 480p and 720p, upscalable to 1080p. The model generates videos in 30+ languages with lip movement synced to each translation, and this model runs behind the video generation API.

Model 2.0, a talking-photo video model, turns one image into a talking video while maintaining visual consistency across long sequences.


Runway Characters creates real-time conversational video agents from a single image.


AI avatar video platform that generates presenter-style videos from a cloned likeness and voice.


Runway API gives developers access to Runway's generative video, image and audio models.


Foundation Models are Mirage's multimodal audio and video models that generate realistic talking videos from text, audio, or images.


TokkingHeads is an AI portrait animation tool that lets users control facial expressions through their camera.


Desktop agentic studio where AI agents build editable product demos and tutorials.


Hera's AI motion designer product generates editable professional motion graphics from text prompts.


AI Studio is VideoDraft AI's browser-based studio where agents generate and produce video, image, voice, and music.


Luma Dream Machine is an AI video generation product that creates cinematic clips from text and images.


A browser-based AI dubbing feature that translates videos into 140-plus languages using voice cloning and lip sync.



Marengo is TwelveLabs' multimodal video embedding model for semantic search, classification, and understanding across video, image, and audio.


Developer API platform for production-ready speech, transcription, music, agents, and audio generation.



Translates video and audio into 10 languages while preserving the speaker's voice, tone, and background audio.



Full-duplex audiovisual foundation model for real-time face-to-face AI conversation.


AI video generation and creative platform built on generative world models.



A web app that turns live video and screen context into a real-time AI body double for video calls.
Runway Characters creates real-time conversational video agents from a single image.

AI avatar video platform that generates presenter-style videos from a cloned likeness and voice.

Runway API gives developers access to Runway's generative video, image and audio models.

Foundation Models are Mirage's multimodal audio and video models that generate realistic talking videos from text, audio, or images.

TokkingHeads is an AI portrait animation tool that lets users control facial expressions through their camera.

Desktop agentic studio where AI agents build editable product demos and tutorials.

Hera's AI motion designer product generates editable professional motion graphics from text prompts.

AI Studio is VideoDraft AI's browser-based studio where agents generate and produce video, image, voice, and music.

Luma Dream Machine is an AI video generation product that creates cinematic clips from text and images.

A browser-based AI dubbing feature that translates videos into 140-plus languages using voice cloning and lip sync.

AI photo generator that creates photorealistic personal images from user photos.

Marengo is TwelveLabs' multimodal video embedding model for semantic search, classification, and understanding across video, image, and audio.

Developer API platform for production-ready speech, transcription, music, agents, and audio generation.

Venice AI API for private, uncensored AI inference.

Translates video and audio into 10 languages while preserving the speaker's voice, tone, and background audio.

AI super agent platform unifying chat, image, video, and voice generation.

Full-duplex audiovisual foundation model for real-time face-to-face AI conversation.

AI video generation and creative platform built on generative world models.

Venice AI app for private AI chat and content generation.

A web app that turns live video and screen context into a real-time AI body double for video calls.
