HeyGen
AI avatar video generation with expressive speech and lip sync
HeyGen develops avatar driven video generation models that produce photorealistic digital presenters with synchronized lip movements, natural facial expressions, and multilingual speech. Their models support text to speech with adjustable speed, pitch, and expressiveness across hundreds of voices and languages, as well as prompt based video creation through their Video Agent. As a Runware provider, HeyGen models are available for avatar video and agentic video generation through a single inference pipeline alongside other creators.
Models by HeyGen
HeyGen Voice 1.0 is HeyGen's text-to-speech model for spoken audio in 39 languages, with the language detected from the text when none is set. It speaks with a public voice or clones a new one from a single recording, and returns the cloned voice so later requests can reuse it. It suits voiceovers, narration for training and product videos, and localized content.
HeyGen Voice 1.0 Turbo is the faster variant of HeyGen Voice 1.0, generating speech in 39 languages from text. It uses the same public voices and the same instant cloning from a single recording, and returns the cloned voice so later requests can reuse it. It suits high-volume narration and pipelines where turnaround matters.
HeyGen Voice 1.0 Turbo Free runs HeyGen Voice 1.0 Turbo on shared, limited capacity. It offers the same public voices, instant voice cloning from a single recording and 39 languages, but response time and availability are not guaranteed. It suits tests, prototypes and small amounts of speech.
HeyGen Video 1.0 is HeyGen's video generation model for short clips with synchronized audio. It generates the full frame from a text prompt, a first-frame image, or up to 12 image, video, and audio references, and produces dialogue, ambience, and sound effects in the same pass, with no separate lip-sync step. It outputs 5 to 30 second clips at 480p, 768p, 1080p, or 2K, suited to presenter shots, product and training content, and social video.
HeyGen Avatar V is an avatar video generation model for talking digital twins and other eligible registered avatar looks. It improves identity preservation, lip sync accuracy, facial expressiveness, and motion coherence across angle changes, scene changes, and long-form videos, making it well suited to presenter, training, and localization workflows where avatar stability matters.
HeyGen Video Agent is an AI video production model that generates complete, multi-scene videos from a single text prompt. It automates the full production pipeline — scriptwriting, avatar selection, shot planning, B-roll integration, motion graphics, captions, and editing — producing broadcast-ready videos with consistent branding. The agent supports customizable avatars, voice cloning, and iterative editing without full regeneration, enabling scalable video content creation for marketing, training, and social media.
HeyGen Avatar IV is a photorealistic AI avatar generation model that creates talking videos from a single image and a script or audio input. The model synchronizes voice with facial motion, expressions, and gestures to produce lifelike avatar performances. It supports multilingual speech, realistic lip synchronization, and expressive body language, enabling scalable production of presenter-style videos without cameras, actors, or studio setups.