HeyGen Video 1.0
HeyGen's general-purpose video model: clips of 5 to 15 seconds with synthesized dialogue, ambience and sound effects, from text, a starting image or reference media, at 480p or 768p.
Video 1.0 is a cloud video-generation model built by HeyGen. It produces short video clips from a text prompt or a starting image. It can also take reference video and audio to guide the result. Clips run up to 30s at 2K with a synchronized audio track. It also supports reference images. It runs through OpenRouter and Runware using your own API key, from about $0.02 per second of output.
- Released
- Sep 2026
- Pricing
- $0.02 per second
- Max resolution
- 2K
- Aspect ratios
- 21:9, 16:9, 4:3 +3 more
- Clip length
- Up to 30s
- Audio
- Synchronized track
- Image-to-video
- Start frame + reference images
Samples
Generated with Video 1.0 via Runware. The same two prompts run against every video model in the catalog (one landscape, one portrait), so the only thing that changes between two models’ clips is the model.
Camera motion, scene coherence over time
Fluid motion, fine detail, temporal stability
HeyGen
HeyGen builds AI video tools and models, including the general-purpose HeyGen Video model for short clips from text, images or reference media.
www.heygen.com ↗HeyGen's text-to-speech model with preset voices on OpenRouter and Runware; on Runware it can also clone a voice from a recording.
A lower-latency version of HeyGen Voice with the same preset voices on OpenRouter and Runware, and voice cloning on Runware.
HeyGen's avatar model, which turns a photo or a short clip of a person into an expressive, lip-synced talking video driven by an audio track, at 1080p or 2K.
The faster, lower-cost tier of HeyGen's Avatar 6, which turns a photo or a short clip of a person into a lip-synced talking video driven by an audio track.
HeyGen's video translation model, which transcribes the speech in a clip, translates it and dubs it in the speaker's own voice with matching lip sync, in many languages.