Ltx 2.3 Lipsync

Ltx 2.3 Lipsync

Playground

LTX-2.3 Lipsync generates talking head videos from audio with synchronized lip movements and natural facial expressions. Built on DiT-based architecture with improved audio-visual alignment quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

LTX-2.3 Lipsync is an advanced AI model that generates talking head videos from audio and an optional reference image. Built on the LTX-2.3 DiT-based architecture with improved audio-visual quality, it creates realistic lip-synced videos that match your audio input.

Why Choose This?

• Improved quality Enhanced audio-visual alignment with better lip sync accuracy and natural facial movements.

• Audio-driven generation Automatically generates video with synchronized lip movements from audio input.

• Optional reference image Provide a portrait image to use as the base, or let the model use a default portrait.

• Flexible resolution Supports 480p, 720p, and 1080p outputs to balance quality and cost.

• Automatic duration Video length automatically matches audio duration (5-20 seconds).

Parameters

Resolution Options

How to Use

1. Upload your audio — the audio track that drives the video (5-20 seconds).
2. Upload reference image (optional) — a portrait to use as the base character.
3. Add prompt (optional) — describe the style or motion you want.
4. Select resolution — 480p for iteration, 720p for balance, 1080p for final output.
5. Run — submit and download the lip-synced video.

Pricing

Pricing is based on audio duration (automatically detected):

Best Use Cases

• Talking Head Videos — Generate spokesperson videos from audio recordings.
• Content Localization — Create videos in multiple languages from audio tracks.
• Virtual Presenters — Generate AI presenters for training, marketing, or education.
• Audio-to-Video — Convert podcasts or audio content into video format.
• Character Animation — Bring portraits to life with synchronized speech.

Pro Tips

• Audio quality directly affects lip sync accuracy - use clear audio.
• Provide a frontal portrait image for best results.
• Use prompt to guide facial expressions and style.
• Iterate at 480p to verify results, then render at higher resolution.
• Audio duration is automatically detected - no need to specify manually.

Notes

• Audio duration must be between 5-20 seconds.
• If no reference image is provided, a default portrait will be used.
• Video length automatically matches audio duration.

Related Models

• LTX-2.3 Text-to-Video — Generate video with audio from text.
• LTX-2.3 Image-to-Video — Animate images with synchronized audio.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
  "resolution": "720p",
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-2.3/lipsync" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters