LipSync vs Dynamic Video: what's the difference?

Sendr has two personalisation options built on the same voice cloning technology. They work differently and suit different use cases.

LipSync

LipSync generates a unique video per contact where your lips are synced to a personalised AI voiceover in your own cloned voice. The result looks like you recorded a personal video for each person.

• Uses your own voice, cloned from your recording
• Also regenerates your lip movement to match the personalised audio
• Uses your regular credits (there is no separate LipSync credit pool)
• Best for: full-frame talking-head videos where your face is clearly visible
• Processing time: typically seconds to minutes, longer at peak times

Dynamic Video

Dynamic Video clones your voice and personalises the spoken word, but does not regenerate lip movement. It's the audio-only counterpart to LipSync.

• Uses your own voice, cloned from your recording
• Skips lip regeneration, so it also works for audio-only voicenotes
• Lower cost and faster to render than LipSync
• Best for: small on-page videos where lip movement isn't clearly visible, or standalone voicenotes
• Processing time: faster than LipSync
• Tip: combine it with Dynamic Video Background so the background dynamically shows the contact's website or LinkedIn profile while the audio is personalised too, giving you a fully personalised video without needing lip-sync.

Which to use

Use LipSync when your video is full-frame and your face is clearly visible, the lip sync is what sells the personal touch. Use Dynamic Video when your video is small on the page (lip movement won't be noticeable anyway) or when you're sending a voicenote instead of a video, it gives nearly the same personalised feel at a lower cost.