Sync Lipsync-2 synchronizes lip movements in any video to supplied audio, enabling realistic mouth alignment for films, podcasts, games, or animations. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Ожидание
$0.05за запуск·~20 / $1
Lipsync 2.0 is a zero-shot lipsync model that takes an existing video and a separate audio track, then re-animates the mouth so lip movements match the speech. No training or fine-tuning is required, and it preserves the speaker’s style across languages, dubbing scenarios, and character types.
video* Source video to be re-dubbed (URL or upload). Use clips where the face is clearly visible and not heavily occluded.
audio* Target speech audio (URL or upload). The lips will be synced to this track.
sync_mode Strategy for matching video and audio durations when they differ:
bounce – Ping-pong the video to cover a longer audio span.
loop – Loop the video until the audio finishes.
cut_off – Truncate to the shorter of video/audio.
silence – Pad with silence or frozen frames where needed.
remap – Time-remap to better align audio and video over the full clip.
Output: a re-synced MP4 video with lips matching the provided audio.
Pricing is linear in video length:
Examples:
| Video length | Price |
|---|---|
| 5 s | $0.25 |
| 10 s | $0.50 |
| 30 s | $1.50 |
| 60 s | $3.00 |
WaveSpeedAI / InfiniteTalk WaveSpeedAI’s single-avatar talking-head model that turns one photo plus audio into smooth, lip-synced digital presenter videos for tutorials, marketing, and social content.
WaveSpeedAI / InfiniteTalk Multi Multi-avatar version of InfiniteTalk that drives several characters in one scene from separate audio tracks, ideal for dialog-style explainers, interviews, and role-play videos.
Kwaivgi / Kling V2 AI Avatar Standard Cost-effective Kling-based AI avatar model that generates natural talking-face videos from a single reference image and voice track, suitable for everyday content and customer support.
Kwaivgi / Kling V2 AI Avatar Pro Higher-fidelity Kling V2 avatar model for premium digital humans, offering smoother motion, better lip-sync, and more stable faces for commercials, brand spokespeople, and product demos.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/sync/lipsync-2 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Lipsync 2 below.
set -euo pipefail
: "${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-2" \
-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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/sync/lipsync-2";
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));
}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-2", 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 2 is a Sync model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. Sync Lipsync-2 synchronizes lip movements in any video to supplied audio, enabling realistic mouth alignment for films, podcasts, games, or animations. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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-2.
Lipsync 2 starts at $0.050 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.
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-2.
Median end-to-end generation time on WaveSpeedAI is around 137 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
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.