Sync Labs · Audio model

Sync Labs Lipsync 1.9 / 2

AI lipsync that preserves each speaker's natural style, by the second.

Generate on Coinis Read the docs

One API key. Every model.

per second
Example
AI audio
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with Sync Labs Lipsync 1.9 / 2.

One model. Three ways to call it. Same key, same bill.

Sync Labs lipsync-2

Audio generation

One call. Same key. Same bill.

$0.07 / second

Sync Labs lipsync-1.9 (legacy)

Audio generation

One call. Same key. Same bill.

$1.93 / minute

Capabilities

What it does best.

Sync Labs lipsync capabilities

Resolution and format

  • Generates face regions at 512x512 resolution[^1]
  • Accepts MP4 video and WAV or MP3 audio via URL, direct upload, or asset ID[^2]

Conditioning controls

  • Temperature parameter (0 to 1, default 0.5) to dial expressiveness of lip movements[^3]
  • Optional occlusion detection (occlusion_detection_enabled) improves accuracy on partially obstructed faces, at the cost of slower generation[^4]
  • Active Speaker Detection (ASD) isolates the correct speaker in multi-person videos[^5]

Language and dubbing

  • Supports dubbing into 29 languages via the platform[^6]

Throughput and delivery

  • Batch processing of up to 500 videos in a single API call (Scale+ plans)[^7]
  • Rate limit of 60 requests per minute on POST /v2/generate[^8]
  • Webhook notifications for async status updates[^9]

SDKs

  • Python 3.8+ (pip install syncsdk) and TypeScript/Node.js 18+ (npm i @sync.so/sdk)[^10]

Known limitations

  • Lipsync 2 requires the speaker to be actively moving in the source video. Still frames and static segments cannot be lipsynced. The model processes input in 2-second independent chunks and needs visual motion in each chunk[^11]
  • Human-like faces only. Animals and non-humanoid characters are not supported[^12]
  • Extreme profile and non-frontal angles produce weaker results on lipsync 2. Sync-3 handles those angles better[^13]
API

Call Sync Labs Lipsync 1.9 / 2 in three lines.

One key. One base URL. Same SDK shape you already use. 

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/audio/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.audio.generate({
  model: "models/sync-labs/sync-labs",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.audio.generate(
    model="models/sync-labs/sync-labs",
    prompt="neon city, rain, tracking shot",
)
Response 
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/sync-labs/sync-labs",
  "output": {
    "video_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

Sync Labs Lipsync 1.9 / 2 · Sync Labs lipsync-2
0.7 tokens
per second · $0.07
Lipsync
$0.07 / second
One key. Every model. One invoice. 1 token = $0.10
8s clip ≈ 6 tokens ($0.56)
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

Sync Labs lipsync-2

Final renders, studios
Resolution —
Price $0.07 / second

Sync Labs lipsync-1.9 (legacy)

Rapid tests, high volume
Resolution —
Price $1.93 / minute
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

E-learning and training localization Record your course once. Re-sync the instructor's mouth to translated audio in any of 29 supported languages. Learners get a native-language video that looks like it was filmed that way.

Personalized video at scale One recording becomes thousands of individually addressed video messages. Swap the audio, keep the face, and deliver outreach without re-shooting.

Film and YouTube dubbing Dub long-form content for global audiences without visible mouth mismatch. Lip movements follow the new audio track, not the original dialogue[^6].

In-game character and entertainment VO Connect Sync Labs to your character pipeline via API. Drive mouth animation from any voice line, in any language, without manual rigging.

End-to-end AI dubbing pipelines Pair Sync Labs lipsync 2 with a text-to-speech model inside Coinis Flow to build a fully automated dubbing workflow. Translate the script, synthesize the audio, and lipsync the video in one connected pipeline[^14].

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

Sync Labs Lipsync 1.9 / 2 FAQs

How much does Sync Labs lipsync cost on Coinis?

Sync Labs lipsync-2 is priced at $0.068 per second on Coinis, with no monthly subscription required. Sync Labs lipsync-1.9 (legacy) is available at $1.925 per minute. You pay only for what you generate, billed alongside every other model in the Coinis catalog.

What is the difference between lipsync-2 and lipsync-1.9?

Lipsync 2 is the current flagship. It preserves each speaker's individual speaking style and supports advanced controls including temperature, occlusion detection, and Active Speaker Detection. Lipsync 1.9 is the legacy model. It uses generic lip movements and is faster, making it a reasonable choice for bulk workflows where style fidelity is less critical. Sync Labs officially recommends lipsync 2 or newer for best results.

Can Sync Labs lipsync a still image or photo?

No. Lipsync 2 and lipsync 2 Pro require the speaker to be actively moving and talking in the source video. The model processes input in 2-second independent chunks and needs visual motion cues in each chunk. Static segments and still photos cannot be lipsynced with these models.

Does Sync Labs AI lipsync work for non-English languages and dubbing?

Yes. The platform supports dubbing into 29 languages. The typical workflow is to supply translated audio alongside the source video. The model re-syncs mouth movements to match the new language track. You can build a fully automated pipeline by pairing lipsync 2 with a TTS model inside Coinis Flow.

Is there an API for Sync Labs lipsync, and what are the rate limits?

Yes. The primary endpoint is POST /v2/generate, rate-limited to 60 requests per minute. Webhooks are available for async status notifications. Official SDKs exist for Python 3.8+ and TypeScript/Node.js 18+. The Coinis API surfaces lipsync 2 at POST /v1/audio/generate using the variant ID sync-lipsync-2.

Does Sync Labs work on profile shots or animated characters?

Lipsync 2 performs best on near-frontal faces. Extreme profile angles and non-frontal shots produce weaker results. For challenging angles, Sync-3 is the recommended model. Sync Labs does not support animals or non-humanoid characters. Only human-like faces are supported across the entire model family.

How do I batch-process hundreds of videos with Sync Labs lipsync?

The batch API accepts up to 500 videos in a single call. Batch processing is available on Scale and higher plans from Sync Labs directly. On Coinis, you can fire individual API calls at up to 60 requests per minute or use Coinis Flow to orchestrate bulk runs without managing the queue yourself.

Related

Pair it with.

Deepgram Nova-3 / Aura-2

Model

ElevenLabs (Multilingual / Turbo / Music)

Model

OpenAI Whisper

Model

All audio models

Catalog
Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .