HeyGen Updates

www.heygen.com

Introducing HeyGen Voice Speech-to-Speech

by Tony Faccenda

You can now record a line on your phone or laptop and get it back in your HeyGen Voice. Speech-to-speech keeps the emotion, timing, pacing, emphasis, and pronunciation from your recording and changes only the voice. What’s

Introducing HeyGen Voice

by Tony Faccenda

HeyGen Voice is our new voice model, and the first built to adapt to video. It ranks first on Artificial Analysis’ voice leaderboard. It delivers your script in your voice, with your pacing and expression, while adapting to the scene’s

HeyGen Voices now supports ElevenLabs v4

by Tony Faccenda

A great script can fall flat when the voice doesn't sound like it means it. ElevenLabs’ v4, their most expressive text-to-speech model yet, is now available in HeyGen Voices. More natural delivery: v4 reads a script like a voice actor

Introducing Look Packs

by Tony Faccenda

Look Packs is now available inside HeyGen. It takes a single face upload and generates a full set of polished images for your AI avatar, powered by HeyGen's new image engine. Upload your face, and it produces a coordinated set of looks

Introducing Speech Cleanup

by Tony Faccenda

Speech Cleanup is now available inside HeyGen. It takes a single recording and automatically removes the parts you would normally edit out or re-record, then stitches the remaining footage into one continuous take. Upload a video (MP4,

Introducing Edit Styles for HeyGen Mobile

by Justin Witcoff

Turn your avatar videos into post-ready content in seconds. Pick from 12 templates that automatically add visual hooks pulled from your script, word-synced captions, and dynamic zoom effects to any video—no timeline, no caption

Introducing Edit Styles for HeyGen Mobile

Introducing our new Video Agent

by Justin Witcoff

The new and improved Video Agent We completely rebuilt Video Agent from the ground up. What's new: Blueprint-first creation See your full video plan before anything renders—avatar, voice, visuals, and scene-by-scene breakdown. Make

Introducing our new Video Agent

Create your Avatar in 15 seconds

by Justin Witcoff, Product Marketing Manager

We cut avatar creation from 5 minutes to 15 seconds. What's new: A new guided flow lets you create your avatar with a single 15-second webcam recording. That one recording captures your appearance, voice, motion, and consent - everything

Introducing Voice Doctor

by Justin Witcoff, Product Marketing Manager

Voice Doctor is a chat-based workflow for fixing the issues you only notice after hearing your voice. Describe what’s wrong in your own words. Hear instant improvements. Save the version that actually sounds like you.

Newer