Choose the correct Lip Sync route
Free simplified Lip Sync
Use /products/lip-sync. It does not require sign-in or use account credits. It offers up to three free generations daily and produces 576px output.
The simplified route accepts uploaded or preset video and audio. It does not accept YouTube video.
Full Lip Sync editor
Use /create/lip-sync. Generating requires sign-in and uses credits. It accepts uploaded, preset, or YouTube video. Audio can come from an upload, preset, or voice-generation option.
Modes
Lite: faster and more affordable for simple clips. Available on Basic and paid plans.
Standard: balanced, realistic lip sync. Available on Basic and paid plans. The source needs visible mouth movement.
Pro: higher detail for teeth, beards, and facial texture. Requires Creator or higher and visible mouth movement.
Duration and timing
Standard and Pro support selections up to 30 minutes.
Lite uses the current clip and credit limit shown by the editor rather than one fixed duration.
The selected video cannot be longer than the available audio.
If the selected video and audio differ in length, output uses the shorter selection.
Lip Sync changes visible mouth movement to follow supplied audio. It does not retime the full video, change audio tempo, or guarantee that mismatched performances align perfectly.
Uploads
Video: MP4, M4V, MOV, and WEBM.
Audio: MP3, WAV, AAC, FLAC, WEBM, WEBA, M4A, OGA, and OGG.
Use one clearly visible face and clear audio. Multiple faces, profile faces, and obstructed faces have no supported selection workflow and are best-effort.
Still images
Use /create/ai-talking-photo for a still image.
Resolution, watermark, and credits
The Create editor supports up to 576px on Basic, 1024px on Creator, 1472px on Pro, and 4096px on Business, without enlarging beyond the source. The displayed estimate is authoritative. Basic output is watermarked unless the account has a credit pack; paid plans and pack purchasers receive watermark-free output.
Troubleshooting
No mouth movement: keep the face and mouth visible. Standard and Pro require source mouth movement.
Audio starts late: adjust the audio start and end positions.
Output ends early: compare selected video and audio lengths.
Still image: switch to Talking Photo.
Send support the project link or visible ID, route, mode, clip length, audio source, and screenshot.