Infinitetalk Fast Video To Video API Documentation

Infinitetalk Fast Video To Video API Documentation

Playground

Audio-driven infinitetalk-fast turns one video plus audio into realistic talking or singing videos with lip-sync. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

What is InfiniteTalk?

InfiniteTalk creates new videos by combining an input silent video and an audio track. It ensures precise lip synchronization while aligning head, face, and body movements with the audio. With optional masking and prompting, you can control which areas move and how the scene appears. The model also maintains visual identity for natural and consistent results.

Why it looks great

• Accurate lip synchronization: matches lip motion precisely to the audio.
• Full-body coherence: aligns head pose, facial expressions, and posture with speech.
• Mask control: optional mask images let you define which regions can move.
• Instruction following: prompts can guide style, pose, or behavior.
• Identity preservation: ensures consistent visual identity across all frames.

How to Use

1. Upload the audio file.
2. Upload a video as the base.
3. (Optional) Upload a mask image to control which regions can move.
4. (Optional) Write a prompt to guide the style, pose, or expressions.
5. Set the seed if you want reproducibility.
6. Submit the job and download the generated video.

Note

• Max clip length per job: 10 minutes
• Processing speed: ~10–30 seconds of wall time per 1 second of video (varies by resolution and queue load)
• Mask safety tip: Do not upload the full image as mask_image. The mask should only cover the regions you want to animate—otherwise the result may render as fully black.

Pricing

> Billing duration: Input media duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds. Existing per-5-second rate tables remain unchanged.

More Versions

• Single-character version
• Multi-character version
• Video-to-video multi-character version

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",
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/infinitetalk-fast/video-to-video" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) 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