> For the documentation index, fetch https://sync.so/docs/llms.txt. Append .md to a page URL for Markdown. Documentation-search MCP: https://sync.so/docs/_mcp/server. # Media Content Tips > Follow these practices for your input video and audio content to get the best results when using sync. labs. The quality of your input media has a direct impact on the final lipsync output. For optimal results, please follow these tips for preparing your video and audio content. ## Tips for Video Content #### Avoid profile views and obstructions For best performance, avoid full profile (side-view) shots and obstructions covering the face. #### Ensure Natural Talking Motion The model performs best when the character in the video appears to be talking naturally. It will preserve the speaker's style during lipsync. > **Note** > > **Tip for AI-Generated Video**: When creating videos with third-party AI video generation models, include this instruction in the text prompt: `"the character should be speaking naturally"`. The generated AI video will have some random mouth movements, which are necessary to get the best results from our lipsync model. ## Tips for Audio Content #### Use clear audio For best performance, avoid audio with music, background noise, or multiple simultaneous speakers. ## Sync Mode Options When your video and audio have different durations, you can choose how to handle the mismatch using the [`sync_mode`](/api-reference/api/generate-api/create#request.body.options.sync_mode) parameter. See the [Sync Mode guide](/developer-guides/sync-mode) for the full behavior matrix and output duration examples. > **Info** > > Sync mode only applies to video inputs. For image inputs (sync-3), sync mode is ignored since images have no intrinsic duration to compare against the audio. #### bounce When video is shorter than audio, the video will reverse playback at the end to match audio duration. Otherwise, video is cropped to match audio. #### loop When video is shorter than audio, the video will loop from the beginning to match audio duration. Otherwise, video is cropped to match audio. #### cut\_off When audio is longer than video, the audio will be cut off to match video duration. Otherwise, video is cropped to match audio. #### silence When video is longer than audio, silence will be added to the audio to match video duration. When audio is longer than video, the output keeps the full audio duration. #### remap The video playback speed will be adjusted (sped up or slowed down) to exactly match the audio duration, preserving all content from both. > **Note** > > **Default Sync Labs Mode**: The default depends on your generation type and video/audio durations: > > * **Non-segmented generations**: > * Video longer than audio: `cut_off` is the default > * Audio longer than video: `bounce` is the default > * **Segmented generations** (using `segments_secs` or `segments_frames`): `remap` is the default, recommended to avoid abrupt cuts mid-video. > **Note** > > **Choosing the Right Sync Labs Mode**: Use `bounce` or `loop` for short videos with longer audio, `cut_off` when you want to prioritize video length, `silence` when you want to preserve the full video, and `remap` when you need to preserve all content from both video and audio. ## Media Content Reference ### Video Input Requirements | Field | Requirement | | :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------- | | Face visibility | Front-facing or slight angle; avoid full profile (side-view) shots | | Face obstructions | No hands, masks, or objects covering the face | | Talking motion | Character should appear to be talking naturally for best results | | AI-generated video tip | Include "the character should be speaking naturally" in the generation prompt to produce random mouth movements that improve lip sync quality | ### Audio Input Requirements | Field | Requirement | | :---------------- | :-------------------------------------------------------------------- | | Speech clarity | Clear speech with minimal background noise | | Background music | Avoid audio with music or overlapping sounds | | Multiple speakers | Avoid audio with multiple simultaneous speakers | | Format | See Media Formats Support page for supported audio formats and codecs | ### Sync Labs Mode Reference | Mode | Behavior | Best For | | :-------- | :------------------------------------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------- | | `bounce` | When video is shorter than audio, video reverses playback at end to match audio duration. When audio is shorter, video is cropped to match audio. | Short videos with longer audio | | `loop` | When video is shorter than audio, video loops from beginning to match audio duration. When audio is shorter, video is cropped to match audio. | Short videos with longer audio | | `cut_off` | When audio is longer than video, audio is cut off to match video duration. When video is longer, video is cropped to match audio. | Prioritizing video length | | `silence` | When video is longer than audio, silence is added to audio to match video duration. When audio is longer, output keeps the full audio duration. | Preserving full video or full audio length | | `remap` | Video playback speed is adjusted (sped up or slowed down) to exactly match audio duration. | Preserving all content from both video and audio | ### Sync Labs Mode Defaults | Generation Type | Condition | Default Mode | | :----------------------------------------------------- | :---------------------- | :----------- | | Non-segmented | Video longer than audio | `cut_off` | | Non-segmented | Audio longer than video | `bounce` | | Segmented (using `segments_secs` or `segments_frames`) | Any | `remap` |