HeyGen Video 1 (Text-to-Video)
HeyGen Video 1 turns a prompt into a 5 to 30 second clip with its own sound (dialogue, ambience, effects), from 480p to 2K, from $0.02 a second.
HeyGen Video 1 is HeyGen's video model, built on MiniMax H3 and post-trained by HeyGen. It makes the picture and its sound in one pass: dialogue, ambience and sound effects. On the Artificial Analysis video arena (2026-11-17) it ranks first among text-to-video models without sound and eighth with sound.
Use it for presenter shots, product and training clips and social video, from 5 to 30 seconds in 480p, 768p, 1080p or 2K and six aspect ratios. prompt_enhancement sets how the model expands your prompt before it renders; disabled uses it as written.
Inputs: prompt (up to 32,000 characters), duration (5-30 seconds, 5 by default), resolution (480p, 768p, 1080p or 2k; 768p by default), aspect_ratio (21:9, 16:9, 4:3, 1:1, 3:4 or 9:16), prompt_enhancement and seed. Outputs: video and seed.
Price per second of video: $0.02 at 480p and 768p, $0.06 at 1080p and 2K. The default 5-second 768p clip costs $0.10, 30 seconds at 2K $1.80. It works from text: to start from a picture, use HeyGen Video 1 (Image-to-Video). It is not a talking-avatar model (it does not lip-sync a given photo to a given voice) and it does not edit an existing video.
- Text to Video
Price: From $0.02 per second of duration, depending on resolution. One run with default settings costs $0.10.
Run HeyGen Video 1 (Text-to-Video) via API
curl -X POST https://api.flymy.ai/api/v1/flymyai/heygen-video-1-text-to-video/predict \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A barista smiles and says: your latte is ready. Soft cafe ambience","duration":5,"resolution":"768p"}'API documentation · Create a free account · Pricing