What is LipSync and how does it work?

LipSync is Sendr's AI video personalisation feature. It takes a video you record of yourself and generates a unique version of it for each contact in your table, with your lips moving in sync to a personalised voiceover addressed to them by name.

The result is a video that looks and sounds like you recorded it individually for every person, without actually doing so.

How it works

1. You record one source video of yourself speaking
2. Sendr clones your voice from that recording and generates a personalised audio track for each contact
3. LipSync combines the audio with your video, syncing your lip movements to the new audio
4. A unique video is generated for each contact, added as a column in your campaign table, and embedded in their personalised page

What you need

• A recorded source video
• LipSync credits

Your voice clone is created from your source video when you set up the LipSync, so there is no separate step beforehand. See "Creating a voice clone".

LipSync credits are separate from your main credits. See "Understanding credits: how they work and what they cost" for details on the LipSync credit pool.

Processing time

LipSync videos typically take 1 to 3 minutes to generate. During peak periods, processing can take up to 24 hours. If a generation fails, the LipSync credits are refunded to your pool, usually within an hour.