MiniMax H3 Open Weights | Try in Video Generator →

Sync Lipsync 3 | AI Digital Human API

sync/

Sync Lipsync 3 synchronizes lip movements in any video to supplied audio using zero-shot lip-sync technology. Supports multiple sync modes for handling duration mismatches, works with live-action, 3D characters, and AI-generated avatars. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

digital-human
Input

Idle

$0.134per run·~74 / $10

ExamplesView all

Related Models

README

LipSync-3

LipSync-3 is Sync's advanced lip synchronization model. Upload a video and an audio track — the model automatically syncs the speaker's lip movements to the new audio with high accuracy and natural motion. Supports multiple sync modes to handle length mismatches between video and audio.

Why Choose This?

  • High-accuracy lip synchronization Precisely maps audio phonemes to lip movements for natural, believable sync across a wide range of speakers and languages.

  • Flexible sync mode control Choose how the model handles video-audio length mismatches — loop, bounce, cut off, silence, or remap — to fit your specific use case.

  • Broad video compatibility Works on talking head videos, interviews, presentations, and any footage with visible facial movement.

  • Simple two-input workflow Just a video and an audio file — no manual keyframing, no masking, no technical setup required.

Parameters

ParameterRequiredDescription
videoYesInput video to apply lip sync to (URL or file upload).
audioYesAudio track to sync the lip movements to (URL, file upload, or microphone recording).
sync_modeNoHow to handle video-audio length mismatches. Options: bounce, loop, cut_off (default), silence, remap.

Sync Mode Options

  • cut_off — Cuts the output at whichever is shorter, video or audio.
  • loop — Loops the video to match the length of the audio.
  • bounce — Plays the video forward then backward repeatedly to match audio length.
  • silence — Pads the shorter input with silence or a still frame to match the longer one.
  • remap — Remaps the video timing to match the audio duration.

How to Use

  1. Upload your video — provide the talking head or speaker video via URL or drag-and-drop.
  2. Upload your audio — provide the replacement audio track via URL, file upload, or microphone recording.
  3. Select sync_mode (optional) — choose how to handle length differences between the video and audio.
  4. Submit — generate, preview, and download your lip-synced video.

Pricing

$0.134 per second of input video.

Best Use Cases

  • Dubbing & Localization — Replace the original audio with a translated voiceover and sync lip movements to match.
  • Voice Replacement — Swap out a speaker's audio while maintaining natural facial animation.
  • AI Avatar Video — Generate talking head videos with custom audio for virtual presenters and digital avatars.
  • Content Repurposing — Update or correct existing video audio without reshooting.
  • Accessibility — Create lip-synced versions of content for accessibility and localization workflows.

Pro Tips

  • Use clean, well-lit talking head footage with a clearly visible face for the most accurate sync results.
  • Minimize background noise in your audio track — cleaner audio produces better phoneme mapping.
  • If your audio is shorter than your video, use cut_off or silence mode depending on whether you want the video trimmed or padded.
  • For seamless looping content, bounce or loop modes work well when the video is shorter than the audio.

Notes

  • Both video and audio are required fields.
  • Pricing is based on the duration of the input video at $0.134 per second.
  • Ensure video and audio URLs are publicly accessible if using links rather than direct uploads.
Note:This website uses AI models provided by third parties.

Lipsync 3 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/sync/lipsync-3 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Lipsync 3 below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "sync_mode": "cut_off"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/sync/lipsync-3" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/sync/lipsync-3";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "sync_mode": "cut_off"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "sync_mode": "cut_off"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/sync/lipsync-3", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Lipsync 3 API — Frequently asked questions

What is the Lipsync 3 API?

Lipsync 3 is a Sync model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. Sync Lipsync 3 synchronizes lip movements in any video to supplied audio using zero-shot lip-sync technology. Supports multiple sync modes for handling duration mismatches, works with live-action, 3D characters, and AI-generated avatars. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Lipsync 3 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/sync/sync-lipsync-3.

How much does Lipsync 3 cost per run?

Lipsync 3 starts at $0.13 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Lipsync 3 accept?

Key inputs: `video`, `audio`, `sync_mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/sync/sync-lipsync-3.

How do I get started with the Lipsync 3 API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Lipsync 3 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Sync). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.