Tasks and inputs
HeyGen Video 1 is listed for Image-text-to-video, Image-to-video, Text-to-video. It accepts text, image, video, audio and produces video. Use the publisher’s input format and preprocessing for your chosen deployment.
HeyGen Video 1 generates 5 to 30 second MP4 clips with audio from text, images or reference media, up to 2K at 24 fps. Built on MiniMax H3.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Pricing conditions: Indicative: from $0.01 per second of video via OpenRouter; 1080p and 2K bill at 3x the 768p rate. Paid API key required. Confirm on your own account.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
A marketing team needs a 15-second vertical clip, with sound, matched to a product photo and a voice sample. That brief is the shape HeyGen Video 1 was built for. HeyGen took MiniMax H3 as the base and post-trained it, and the result accepts text, images, video and audio as inputs and returns a finished MP4.
There are three modes. Text-to-video works from a prompt alone. Image-to-video animates a still. Reference-to-video is the interesting one: you can hand it up to nine reference images, three videos and three audio files in a single request, and it uses them to steer look, motion and sound.
| Setting | Choices |
|---|---|
| API ID | heygen-video-1 |
| Resolution | 480p, 768p (default), 1080p, 2K |
| Frame rate | 24 fps |
| Clip length | 5 to 30 seconds (15 s max on some enhancement settings) |
| Aspect ratios | Six, from 21:9 to 9:16 |
| Audio | Generated AAC track in the MP4 |
| References per request | Up to 9 images, 3 videos, 3 audio files |
One restriction catches people out. The two highest tiers, 1080p and 2K, only render in 16:9 or 9:16. If your layout is square or ultra-wide, you are capped at 768p.
Billing is per second of video, not per token. Through OpenRouter, rates start from $0.01 per second, and 1080p and 2K are charged at three times the 768p rate. A paid API key is required. That multiplier matters: a 30-second 2K clip costs triple its 768p twin, so draft at the default and only upscale the takes you keep. Treat these rates as indicative and check your own HeyGen or gateway account.
HeyGen's catalogue page does not print a release date. The dated listing slug points to 30 September 2026, which is the date we use, but take it as approximate.
Pick five briefs you actually ship, including one with a tricky reference (a logo, a face, a specific product angle). Render each at 768p first. Judge three things: does the generated audio fit, does the reference survive across the whole clip, and how often do you need a second take? Count the retries. A model that is cheap per second but needs three attempts is not cheap.
If you need longer or silent clips, compare against other text-to-video models and image-to-video options before committing a pipeline to it.
Compare the model on the work you need to complete.
HeyGen Video 1 is listed for Image-text-to-video, Image-to-video, Text-to-video. It accepts text, image, video, audio and produces video. Use the publisher’s input format and preprocessing for your chosen deployment.
Choose duration, resolution and frame rate together. Compare the cost of an accepted clip, including repeat generations.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Gemini Omni 1.2 Flash is Google's conversational video generation and editing model, making 3-15 second clips with native audio from 360p to 4K.
Meta
Muse Video is Meta’s previewed video-generation model with native audio; a public Meta Model API route and price have not been established.
Wan-AI
Hugging Face repository for Text-to-video.
AaronHuangWei
Hugging Face repository for Text-to-video.
Abiray
Abiray/LTX-2.3-22B-DISTILLED-1.1-GGUF is a source-linked Hugging Face repository assigned to Text-to-video. Its recorded task interface accepts text and produces video.
Abiray
Abiray/Sulphur-2-base-GGUF is a source-linked Hugging Face repository assigned to Text-to-video. Its recorded task interface accepts text and produces video.