Saltar a la navegación
Compatibilidad y consejos

Media Formats Support

Supported Formats

Video

MIME TypeExtensionFormat
video/mp4.mp4MP4
video/quicktime.mov, .qtQuickTime
video/webm.webmWebM
video/x-msvideo.aviAVI

Audio

Full Support

MIME TypeExtensionFormat
audio/wav.wavWAV
audio/mpeg.mp3MP3
audio/ogg.oggOGG
audio/flac.flacFLAC
audio/alac.alacALAC
audio/mp4.mp4MP4 Audio

Limited Support

The following formats have partial support due to licensing or legal restrictions:

MIME TypeExtensionFormat
audio/x-ms-wma.wmaWMA
audio/x-m4a.m4aM4A
audio/x-m3a.m3aM3A
audio/aac.aacAAC

For best compatibility, use MP4 for video and WAV or MP3 for audio.

Output Quality

All output is re-encoded to H.264 using libx264 (-crf 17 -preset slow), regardless of the input codec. Frames are processed in RGB color space internally during generation, so the original bitrate, frame rate, and color grading may differ in the output.

Don’t rely on bitrate for quality preservation: Outputs are re-encoded and bitrate may change.

HDR is not fully supported: HDR videos are normalized to SDR, which may affect color grading in the output.

Alpha channels are removed: The H.264/RGB pipeline does not support transparency. Alpha channels are replaced with a solid background.

Preserving Color

For color-sensitive H.264 workflows - especially when compositing generated output back onto source footage - use explicit SDR color metadata and 4:4:4 chroma sampling.

  • Tag SDR BT.709 metadata explicitly: Set color_space, color_transfer, color_range, and color_primaries. Untagged or partially tagged files can be interpreted differently across decoders. The pipeline uses ffmpeg 7.1 for color metadata detection.
  • Prefer yuv444p when color accuracy matters: The pipeline operates in RGB. 4:2:0 and 4:2:2 inputs require chroma upsampling during YUV→RGB conversion, which can cause color shifts or compositing seams. 4:4:4 preserves full chroma resolution through that conversion.
  • Export 4:4:4 from your source tool: Converting an existing 4:2:0 file to 4:4:4 cannot restore discarded chroma detail.
  • For lossless or pixel-level workflows, contact support.

Example FFmpeg command for a tagged SDR BT.709 H.264 export:

ffmpeg -i input.mov \
  -c:v libx264 -pix_fmt yuv444p \
  -color_range tv -colorspace bt709 -color_primaries bt709 -color_trc bt709 \
  -crf 17 -preset slow \
  -c:a aac -b:a 192k \
  output.mp4

Video

PropertyRecommended Value
CodecH.264 High Profile for general use; H.264 4:4:4 for color-sensitive work
Resolution1920×1080
Average Bitrate≥ 10 Mbps
Frame Rate24, 25, or 30 fps (constant)
Color Space8-bit SDR BT.709
Color MetadataExplicitly tag range, primaries, transfer, and matrix
Chroma Samplingyuv420p or yuv422p for general use; yuv444p when color preservation is critical

4K maximum: Videos above 4096×2160 are rejected. Downscale to 4K or below before uploading.

Audio

  • Sample rate: 44.1 kHz or 48 kHz. Higher rates are downsampled to 48 kHz, which may reduce quality.
  • Bit depth: Up to 32-bit float.
  • Channels: Up to 7.1. Spatial audio is not supported.
  • Multiple streams: Only the first audio stream is processed; all others are discarded.

Codec Quality Comparison

All input codecs are transcoded to a standard format, so processing speed is consistent. Quality loss varies by codec, measured using VMAF:

Input CodecOutput Quality
H.264Best (least quality loss)
MPEG-2Good (up to 15% quality loss)
H.265Good (up to 15% quality loss)
VP9Fair (up to 20% quality loss)
AV1Fair (over 20% quality loss)

Frequently Asked Questions

Compare the source and generated file before conforming the result to your editing timeline. Run this command for each file:

ffprobe -v error -select_streams v:0 \
  -show_entries stream=r_frame_rate,avg_frame_rate,nb_frames,duration \
  -of default=noprint_wrappers=1 input.mp4

Variable-frame-rate sources can report different nominal and average frame rates. Check both values and the duration instead of assuming that the source and output have identical frame counts.

The application limits uploaded files to 5 GiB per file, subject to your plan’s file size limit. This applies to both asset uploads and direct multipart uploads to POST /v2/generate. Direct uploads may also face lower proxy limits. For large local files, use one of these options:

  • Upload the file as an asset and pass the returned assetId in your input. Retries reuse the asset instead of resending the file.
  • Host the file at a publicly accessible URL (S3 bucket, CDN, or any web server) and pass it in the url field of your input.

URL inputs avoid the direct multipart upload parser limit, but must still meet applicable plan limits and media requirements. For large local files, prefer the upload-first asset flow so generation retries do not resend the file.

Hosted URLs must return the media file itself without authentication headers. A sharing or preview page that returns HTML is not a direct media URL, even if it opens in your browser. For local files or private media, use Asset Uploads and pass the returned assetId.

Maximum duration depends on your plan:

PlanMaximum Duration
Free20 seconds
Hobbyist1 minute
Scale+30 minutes

Check the pricing page for your plan’s specific limit.

  • react-1 has a hard limit of 15 seconds regardless of plan - it is designed for short-form expressive content.
  • For videos exceeding your plan’s limit, use the Segments API to split and process them in shorter chunks.

Yes - any aspect ratio is supported, including vertical (9:16), horizontal (16:9), square (1:1), and custom dimensions.

The pipeline extracts the face region at 512×512 for processing, then composites it back into the original frame. The output always matches the input dimensions and orientation.

For best face detection in vertical videos, ensure the speaker’s face is clearly visible and well-lit.

  • Media Content Tips — best practices for preparing your video and audio content for optimal lip sync results
  • Lipsync Model — learn about supported models and their input requirements
  • Quickstart — get started with your first Sync Labs generation