Log inSign Up
Open Hedra

Hedra Avatar

All models
Video modelHedra

Overview

Hedra Avatar is a specialized video model developed by Hedra, powered by Together AI infrastructure, that generates talking-head videos from a single portrait image and an audio track. Built for long-form content, it can produce uncut videos up to 10 minutes long with accurate lip-sync and natural facial movements. It is well-suited for creators producing on-camera dialogue, explainer videos, and vocal performances, serving as a focused alternative to motion-heavy models like Hedra Omnia.

Best of Hedra Avatar

A close-up, high-angle shot of an elderly, bearded man in a blue coat climbing stone stairs. He holds a glowing lantern in one hand and grips a handrail with the other. This video still, generated at 1280x720 resolution using Hedra, features dark, moody lighting casting shadows on stone walls.Weathered Lighthouse Keeper on Stone Stairs — HedraA medium close-up of a middle-aged man with graying hair wearing an olive green jacket, looking towards the camera. He is standing on the stone pathway of the Great Wall of China, which stretches into the lush green hills behind him. This 1920x1080 resolution video avatar was generated using Hedra.Narrator on the Great Wall of China — Hedra

What is Hedra Avatar best used for?

Hedra Avatar is optimized for generating highly expressive talking-head videos with accurate lip-sync. By pairing a static portrait with an audio file, the model tracks phonemes to naturally match mouth movements and facial expressions to the spoken rhythm. According to the Hedra API documentation, it is ideal for character-driven storytelling, educational videos, and virtual presenters, supporting continuous video generations of up to 10 minutes in length.

How does Hedra Avatar fit into the Hedra model family?

Hedra Avatar evolved from the company's earlier video foundation models, including Hedra Character 3 (released in March 2025) and its predecessors. While Avatar specializes in focused talking-head videos, it sits alongside Hedra Omnia, which was introduced on February 5, 2026. Omnia expands on these core audio-driven capabilities by adding full-body motion, dynamic environments, and cinematic camera control to character-driven content.

How can I get the most consistent characters with Hedra Avatar?

To achieve the best results, the community recommends separating your image generation from your animation step. Use a dedicated image model like Nano Banana 2 to generate a high-quality, static portrait. Once your character design is locked, upload that image alongside your audio file into Hedra Avatar. You can also include an Avatar Behavior Prompt (e.g., 'gestures naturally, occasional smile') to guide the specific emotional expressions and micro-movements during the lip-sync. For more structured prompting, consult Hedra's official prompt guide.

Similar models

Hedra OmniaHedraHedra Character 3HedraKling AI Avatar v2 ProKuaishouKling AI Avatar v2 StandardKuaishouVEED Fabric 1.0VEED

Prompt tips

  • Start with a high-quality portrait: Use a well-lit, front-facing headshot. You can generate a realistic base image using a model like Nano Banana 2 before animating it.

  • Control length via audio: The duration of your final video is dictated entirely by your audio input. For a 3-minute video, provide exactly 3 minutes of audio.

  • Guide expressions with text prompts: Even when driven by audio, you can use text prompts to guide the avatar's behavior (e.g., 'gestures naturally, occasional smile, friendly and relaxed vibe').

  • Optimize your audio: Record or generate your audio in a quiet environment. Clear, high-quality audio produces the cleanest lip-sync and facial mapping.