Sync React 1 API Documentation

Sync React 1 API Documentation

Playground

Sync React-1 is a production-grade video-to-video lip-sync model. It maps any speech track to a target face, producing phoneme-accurate visemes and smooth timing while preserving identity, head pose, lighting, and background. Supports emotion and intensity control, multilingual speech, and long takes for talking-head content. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.

Features

sync/react-1 is a production-ready audio-driven video animation model that syncs a subject in a video to an input audio track. It supports selectable emotion control and multiple animation modes (lips / face / head) to help you generate natural, expressive results for short clips with minimal setup.

Why it stands out

• Audio-to-video sync for fast talking-head and reaction style outputs.
• Emotion presets (happy / sad / angry / disgusted / surprised / neutral) to steer overall expression.
• Multiple control modes so you can animate only lips, or drive broader face/head motion.
• Simple workflow and predictable pricing for quick iteration.

Capabilities

• Audio-driven lip sync for an input video

• Emotion-conditioned expression steering

• Mode control for different animation scopes:

• lips: focus on mouth movement

• face: include facial expression changes

• head: include head motion cues (where supported by the model)

Parameters

Pricing

Pricing is $0.167 per second, based on the input audio duration rounded up to the next whole second.

Billing Rules

• Billable duration is the input audio duration, rounded up to the next whole second.
• The model uses loop mode: shorter videos repeat, while longer videos are trimmed to match the audio duration.
• There is no 5-second billing cap.
• Keep both audio and video inputs within the supported 15-second limit.

How to use

1. Upload the video (best with a clear, front-facing subject).
2. Upload the audio (speech, voiceover, or short dialogue).
3. Choose emotion to steer expression tone.
4. Choose model_mode (lips / face / head).
5. Run the model and download the synced result.

Best Use Cases

• Short talking-head clips for creators and social media
• Dubbing and voiceover sync for character shots
• Expressive reaction clips with controlled emotion
• Rapid prototyping for dialogue-driven video concepts

Notes

• Best results: single subject, stable lighting, minimal motion blur, and a visible face.
• Use lips mode for the most conservative edits; use face/head when you want stronger performance and expression.
• Very long videos are billed at the 5-second cap, so trim to the segment you want to animate.

More Digital Human Models

• wavespeed-ai/infinitetalk — Create realistic talking-head digital humans from a single portrait and audio, delivering stable lip sync and natural facial motion for voice-driven avatar videos.

• wavespeed-ai/infinitetalk/multi — Multi-person talking avatar generation that syncs multiple faces to audio with consistent expressions and timing, ideal for dialogues, interviews, and group scenes.

• kwaivgi/kling-v2-ai-avatar-pro — Pro-grade AI avatar video generation for high-fidelity digital humans with strong identity consistency and polished, production-ready results for marketing and creator content.

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'
{
  "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",
  "emotion": "neutral",
  "model_mode": "face"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/sync/react-1" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters