How do I lip sync a video with multiple speakers or a two-person dialogue?
Last updated: March 31, 2026
Sync currently supports lip syncing one speaker at a time per generation. Here's how to handle multi-speaker content:
For videos with multiple people visible
Sync will detect faces in your video. Use the face selection feature to choose which person's lips should be synced to the audio. See: How do I select which person to lipsync?
For two-person dialogues (podcasts, interviews, etc.)
The recommended workflow is:
Split your audio into separate tracks — one per speaker
Run separate generations — one for each speaker, using their respective audio track
Combine the outputs in your video editor (Premiere Pro, DaVinci Resolve, etc.)
Tips for best results
Keep each speaker's audio isolated — remove crosstalk and overlap where possible
Use the same source video for both generations so timing stays aligned
If using the API, you can run both generations concurrently to save time
Using the Premiere Pro Plugin
The Sync Premiere Plugin works per-clip. For multi-speaker timelines, apply lip sync to each speaker's segment individually within your timeline.
Need help?
If you're working on a complex multi-speaker project and need guidance, reach out to our support team — we're happy to help you plan the best workflow for your specific use case.