HeyGen Avatar V

HeyGen Avatar IV

Turn a portrait image or a preset avatar and a speech recording into a talking video, with up to 1080p output. Portrait mode offers expression intensity, motion directions and an optional background image. Upload WAV or MP3 audio up to 600 seconds and 25 MB. NanoGPT bills input audio duration, rounded up to whole seconds in portrait mode. Text-to-speech is not available.

HeyGen Video 1

Create short scenes with generated dialogue, ambience, and sound effects from a prompt, a first-frame image, or image, video, and audio references. Built on MiniMax H3 and post-trained by HeyGen.

Seedance 2.5 Talking Avatar

Turn a portrait and voice recording into an expressive talking-avatar video with natural lip sync, facial motion, and optional direction for gestures or presentation style. Supports up to 120 seconds at 480p or 720p.

LongCat Avatar 1.5

Upgraded audio-driven talking or singing avatar generation from a single image with sharper lip sync and faster generation. Supports 480p/720p output up to 30 seconds.

LongCat Avatar 1.5 Multi

Audio-driven two-person avatar generation from a single image and left/right audio tracks. Supports simultaneous or sequential dialogue, 480p/720p output, and up to 30 seconds of audio.

P-Video Avatar

Image-and-audio avatar video generation for speech-driven talking-head clips, with 720p and 1080p output.