Sync Support FAQ

Last updated: April 7, 2026

Sync.so Support FAQ

This document contains answers to the most frequently asked questions from customers, organized by category. Use this as a reference for the AI support agent.

Note: Pricing and plan details should be verified against sync.so/pricing for the most current information.


Video & Duration Limits

What's the maximum length of lipsync video I can create?

Video length limits depend on your subscription plan:

PlanMax Video Length

Free

20 seconds

Hobbyist ($5/mo)

1 minute

Creator ($19/mo)

5 minutes

Growth ($49/mo)

10 minutes

Scale ($249/mo)

30 minutes

Enterprise

Custom

For videos longer than your plan allows, split them into segments and process separately.

Do you accept vertical videos?

Yes, Sync supports both horizontal (landscape) and vertical (portrait) video orientations. The output will maintain the same orientation as your input video.

What does "Generate videos up to X minutes long" mean?

This refers to the maximum duration of a single lipsync generation. Higher subscription tiers unlock longer maximum durations per video.


Plan Limits & Usage

How many videos can I create on my plan?

Free tier: 3 free lipsync generations and 10 TTS generations per month.

Paid plans: Unlimited generations. You pay per generation based on usage (calculated by output frames × model price per frame).

What does "Active job limit reached" mean?

This means you have too many generations processing at once. Each plan has a concurrent job limit:

PlanConcurrent Jobs

Free

1

Hobbyist

1

Creator

3

Growth

6

Scale

15

Wait for current jobs to complete, or upgrade for higher limits.

How does the billing model work?

Sync uses a subscription + usage model:

  • Subscription: Unlocks higher limits, premium features, discounts, and access to all models

  • Usage: You pay separately for each generation based on frames (output video frames × per-frame model price)

Once you subscribe, the free generation allowance ends.

What are the model prices?

Usage is billed per frame of generated video and the exact prices depend on the specific plan that you're on:

You only pay for the lipsynced portion, not the full length of your uploaded video. Check sync.so/docs/models/lipsync for current pricing.


Pricing & Billing

What subscription plans are available?

Plan

Price

Duration

Concurrency

Voice Clones

Key Features

Free

$0

20 seconds

1

3

0

Hobbyist

$5/mo

1 minute

1

3

$5 in credits included, API access, SDKs

Creator

$19/mo

5 minutes

3

5

No watermark, use own TTS API key

Growth

$49/mo

10 minutes

6

15

team seats, 5% off usage

Scale

$249/mo

30 minutes

15

50

High-volume production

Enterprise

Custom

Custom

Custom

White-glove support

Subscriptions unlock: higher concurrency limits, longer video durations, premium features, access to all models, and usage discounts.

For custom pricing or higher limits, contact [email protected].

Do you offer discounts or coupons?

We occasionally run promotions. Check our website or contact [email protected] for current offers.

Why was I charged more than expected?

Sync bills for both subscription and usage separately:

  1. Subscription fee: Your plan's base price ($5, $19, $49, etc.)

  2. Usage charges: Based on seconds of video generated (~$0.05/second for standard model)

What happens if my payment fails?

Failed payments are retried for 5 days. If payment continues to fail, your subscription will be cancelled. Unpaid invoices will block further generations until resolved.


How to Use

Where can I write prompts?

Sync Studio does not support text prompts to generate video. However, you can use the text-to-speech feature to generate audio.

In Lite mode:

  1. Upload a video

  2. An input for adding an audio file or writing text for text-to-speech will appear

In Advanced mode:

  1. Click "Generate Speech" to open the text-to-speech input directly

How do I remove watermarks?

Watermarks are only present on Free plan and Hobbyist generations. To remove watermarks:

  1. Upgrade to Creator plan or higher

  2. Re-generate your video

  3. The new output will be watermark-free

How can I find my receipt/invoice?

  1. Go to sync.so/billing

  2. Click "Manage Billing"

This will open up a billing portal where you can view and download all invoices.

Or check your email for receipts sent after each payment.

How do I change the voice from male to female?

When entering text in the text-to-speech input, you can change the selected voice used for generation. Simply click on the voice selector to choose from available voices (organized by gender, style, accent). This works the same way in both Lite and Advanced mode.

How do I select which person's lips to sync in a multi-person video?

// TO BE FILLED

How do I clone my voice?

In Lite mode:

  1. In the text-to-speech input, click "Select voice"

  2. Select "Clone voice" (top option)

In Advanced mode:

  1. Click "Generate Speech" to access the text-to-speech section

  2. Either click "Clone voice" above the "Select voice" input, or click "Select voice" and select "Clone voice" (top option)

For best results when uploading your voice sample:

  • Upload 1-3 minutes of clear audio

  • Use high-quality audio with minimal background noise

  • Speak naturally at consistent volume

  • Avoid music or other speakers in the recording

Note: Hobbyist plan allows up to 3 voice clones. Higher tiers allow more.

How do I download my finished video?

  1. Wait for generation to complete (status: "COMPLETED")

  2. Click the download icon on the video thumbnail or from the top right of the screen (to the left of the profile button)

  3. Or click the video to preview, then use the download button

How do I delete my account?

To delete your account, please reach out to our support team. You can contact us through the support chat or email, and we'll assist you with the account deletion process.

Note: This will cancel any active subscription and delete all projects. This action cannot be undone.


Feature Availability

Do you support lipsyncing on non-human cartoons/animations?

Sync lipsync models support human-like faces only. They do not support animals or non-humanoid characters.

For animated characters with human-like facial features, results may vary depending on:

  • How realistic the character's face is

  • Whether the mouth is clearly visible

  • The animation style

Do you support live audio calls / real-time lipsync?

Real-time/live lipsync is not currently available. Sync processes pre-recorded video and audio. For live streaming use cases, please contact [email protected] to discuss your needs.

Can I use a static image to generate video?

The lipsync models work best when the input video shows natural speaking motion - the speaker should be actively moving or speaking throughout. Still frames or static segments may not produce good results.

If you need to animate a static image, you would need to use an image-to-video model. Sync does not currently offer this feature.

Can I upload a video with no sound and add audio?

Yes! This is a common use case, as long as the video shows natural speaking motion. Simply:

  1. Upload your silent video (with visible lip/face movement)

  2. Upload or generate the audio you want

  3. Sync will add the audio and match the lip movements

Do you have an API?

Yes! Sync offers API access for programmatic integration:

  • RESTful API for all lipsync features

  • Python SDK: syncsdk package

  • TypeScript/JavaScript SDK: @sync.so/sdk package

  • Documentation: sync.so/docs

What models are available?

Lipsync models:

  • lipsync-1.9.0-beta: Fast legacy lipsync for simple videos

  • lipsync-2: Most natural lipsyncing, preserves unique speaking style

  • lipsync-2-pro: Highest quality with diffusion-based super resolution

React model:

  • react-1: Synchronizes lip movements, facial expressions, and head movements to match audio with emotional direction. Limited to 15 seconds per clip.


Language Support

What languages are supported for lipsync?

Sync supports lipsync in virtually any language. The AI analyzes the audio waveform, so it works with:

  • All major languages (English, Spanish, Chinese, etc.)

  • Regional accents and dialects

  • Singing in any language

Can I translate and dub a video into another language with lipsync?

Yes! Workflow:

  1. Generate translated audio (using a service like ElevenLabs)

  2. Upload original video + translated audio to Sync

  3. Sync will match the lips to the new language

The translation itself must be done separately - Sync handles the lipsync portion.

Do you support Vietnamese/Chinese/Spanish/[specific language]?

Yes, lipsync works with all spoken languages. The AI doesn't need to "understand" the language - it matches mouth movements to audio patterns universally.


Processing & Performance

How long does it take to generate a video?

Processing time depends on:

  • Video length

  • Model selected (lipsync-2-pro is 1.5-2x slower than other models)

  • Current system load

Jobs are asynchronous and typically take a few minutes. The quickstart docs recommend polling status every 10 seconds.

My video seems stuck on "Processing" - what should I do?

If processing takes longer than expected:

  1. Wait - some jobs take longer during high load

  2. Check status.sync.so for any ongoing incidents

  3. If still stuck after 30+ minutes, contact support with your job ID

Possible job statuses: COMPLETED, FAILED, REJECTED

Why is my download speed slow?

Download speed depends on:

  • Your internet connection

  • Video file size

  • Server load

Try:

  1. Using a wired connection instead of WiFi

  2. Downloading during off-peak hours

  3. Using a download manager for large files


Voice & TTS

What's better for voice cloning - video or audio recording?

Audio recording is preferred because:

  • Higher audio quality without video compression

  • Easier to get clean samples

  • No background noise from video recording

For voice cloning, upload a clean audio file (MP3 or WAV) with 1-3 minutes of speech.

Why doesn't my cloned voice sound right?

Common issues and fixes:

  1. Poor audio quality: Use high-quality recordings

  2. Too short: Provide at least 1-2 minutes of speech

  3. Background noise: Use clean audio without music/others

  4. Inconsistent tone: Speak naturally and consistently

What voice options are available?

Sync offers:

  • Stock voices: Pre-made voices in various styles, accents, genders

  • Voice cloning: Clone any voice from audio samples

  • ElevenLabs integration: Access ElevenLabs voice library


Common Issues

I just paid but my plan isn't active

This is usually a payment processing delay. Try:

  1. Refresh the page

  2. Log out and log back in

  3. Wait 5-10 minutes for the payment to process

If still not active after 15 minutes, contact support with your payment confirmation.

There's no button to cancel my subscription

To cancel:

  1. Go to sync.so/billing

  2. Click "Cancel Subscription" (this will take you to the billing portal)

  3. Click "Cancel Subscription" in the billing portal

Cancellation takes effect at the end of your billing cycle. There are no cancellation fees, but any usage charges during the period still apply.

If you can't find it, contact support and we'll help you cancel.

Can I get a refund?

Refund eligibility:

  • Available for Hobbyist and Creator tiers only

  • Your frame usage must be ≤1,500 frames

  • Must request within your current billing period

  • Applies only to subscription fees, not usage invoices

  • Can only be refunded once every 90 days

If you meet these criteria, contact support for a refund. For other cases, contact support to discuss your situation.

My video has artifacts or glitches

This can happen due to:

  • Low-quality input video

  • Face partially obscured

  • Profile views, small faces, or moving faces

  • Multiple speakers in frame

Try:

  1. Using a higher quality source video

  2. Converting video to MP4 (H.264 codec)

  3. Ensuring the face is clearly visible and front-facing throughout

  4. Using single-speaker videos for best results

  5. Enabling occlusion_detection_enabled parameter (may slow processing)


Input Requirements

What video formats are supported?

MP4 (H.264 codec) is recommended. The examples in the docs use MP4 for video and WAV for audio.

What are the input requirements for good results?

For best lipsync results:

  • Input video must show natural speaking motion

  • Speaker must be actively moving or speaking throughout

  • Face should be clearly visible and preferably front-facing

  • Single speaker works best (multi-speaker may reduce quality)

  • Face resolution in output: 512×512 pixels

Challenging scenarios that may reduce quality:

  • Multiple speakers

  • Profile views

  • Small faces

  • Obstructed/occluded faces

  • Moving/unstable camera


Contact

For issues not covered here: