Replace the speech in an existing clip with a new audio track. Lipsync 2 Pro aligns the mouth movement with that recording; it does not create a presenter from a photo or write a translation for you.
Add your source
Direct the result
Review the setup
Generate & refine01Real VlogMe comparison
The original is a presenter clip made with Hedra in VlogMe. The result uses the same shot, a Spanish ElevenLabs voice track and Lipsync 2 Pro in Video Studio. The line means “Your first hire shouldn't be a boss. Here's who to hire.” Compare the mouth movement as well as the sound; this is a genuine workflow example, not a universal quality guarantee.
02Match the task to the inputs
01Correct a line
Use a new recording when a short presenter line, offer or pronunciation needs to change. Prepare the revised audio at a pace that fits the original performance. Large timing differences, rapid head turns or an obscured mouth can make a replacement less convincing; review those moments carefully.
02Localize a finished clip
If you already have approved translated audio, lip sync can fit it to the existing video. This workflow does not translate or generate that audio automatically. For a full video-dubbing project with a target language, use DUB instead; for new narration from text, start in Audio Studio.
03Start from a portrait
A still image and a script do not meet this lip-sync tool's two-input requirement. Use the talking-avatar generator to animate a portrait first. Once you have a finished video, return here if you need its mouth movement synchronized with another recording.
03From replacement audio to a finished clip
Select both files above, then sign in. Each file is handed to its own slot: video stays video and the replacement recording goes into the audio slot. Neither file is generated or charged on this landing page.
Video Studio opens the Lipsync 2 Pro workflow. Check both inputs and the current credit estimate. The shorter input sets the synced length, so prepare matching durations when you need the full performance.
After generation, watch with sound and compare to the source. Check lip timing, teeth, face edges and moments when the head turns. Save a final clip only after reviewing the whole result.
This workflow needs a replacement audio file. Generate a voiceover from your script in Audio Studio or record the line yourself, then supply the finished audio alongside your video.
Not by itself. It synchronizes a video with audio you provide. Use DUB when you want a target-language video workflow, or bring an already translated recording to this page.
Choosing files and opening the studio do not launch a generation. Processing uses paid credits. The studio shows the estimate for the selected clip before you confirm; plan and credit-pack details are on the pricing page.
Use a clear, visible speaking face and an audio track with a sensible pace for the performance. Covered mouths, very fast movement, overlapping speakers or strongly mismatched durations can reduce quality. You must have permission to use both the source video and the voice.
The starter keeps your selected files in this browser until you continue. After sign-in, they upload to Lab and populate the separate video and audio inputs. Keep the same browser; if its storage is unavailable or the draft expires, the app will ask you to add the files again.
A new voice for an existing shot
Prepare the pair, review the price and control when the lip-sync task starts. No automatic generation at sign-in.
