Infinitetalk Fast Video To Video Multi

Infinitetalk Fast Video To Video Multi

Playground

InfiniteTalk fast video-to-video multi converts a video and two audio inputs into multi-character talking or singing videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

InfiniteTalk Fast Video-to-Video Multi is the speed-optimized version of InfiniteTalk, creating lip-synced videos for multiple characters at half the cost. Upload a video with two characters and their audio tracks — the model generates accurate lip synchronization with fast processing, perfect for high-volume content production.

Why Choose This?

• Fastest processing Speed-optimized for quick turnaround on multi-character lip sync projects.

• Half the cost 50% cheaper than the standard version — ideal for high-volume production.

• Multi-character lip sync Synchronizes lip motion precisely with audio for two characters simultaneously.

• Flexible speaking order Choose meanwhile (simultaneous), left_right, or right_left speaking patterns.

• Full-body coherence Captures head movements, facial expressions, and posture changes beyond the lips.

• Long-form support Process videos up to 10 minutes in length.

Parameters

How to Use

1. Upload your video — provide a video clearly showing two people.
2. Upload left audio — add audio file for the left character.
3. Upload right audio — add audio file for the right character.
4. Write prompt (optional) — guide scene, pose, or behavior.
5. Select speaking order — choose meanwhile, left_right, or right_left.
6. Run — submit and download your lip-synced video.

Pricing

Billing Rules

• Rate: $0.015 per second ($0.075 per 5 seconds)
• Minimum charge: 5 seconds ($0.075)
• Maximum duration: 600 seconds (10 minutes)
• Duration calculation:
• Sequential (left_right / right_left): left_audio + right_audio
• Simultaneous (meanwhile): max(left_audio, right_audio)

Best Use Cases

• High-Volume Production — Cost-effective lip sync for large content libraries.
• Dialogue Scenes — Create realistic conversations between two characters.
• Social Media Content — Quick turnaround for multi-character videos.
• Podcast Visuals — Add visual elements to two-person podcast recordings.
• Rapid Prototyping — Test concepts before using the standard version.

Pro Tips

• Use Fast version for iteration and testing, standard version for final quality.
• Ensure both characters are clearly visible in the source video.
• Use “meanwhile” for overlapping dialogue or simultaneous speech.
• Use “left_right” or “right_left” for sequential conversation flow.
• Mask only the regions you want to animate — full image masks result in black output.

Notes

• Maximum video length: 10 minutes (600 seconds).
• Processing time: faster than standard version.
• Mask safety: Do not upload the full image as mask — only cover animatable regions.
• Ensure uploaded file URLs are publicly accessible.

Related Models

• InfiniteTalk Video-to-Video Multi — Standard version with 720p support.
• InfiniteTalk Fast Video-to-Video — Fast single-character version.
• InfiniteTalk Fast Multi — Fast multi-character image-to-video.

Reference

• Build your own digital human

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",
  "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
  "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
  "order": "meanwhile",
  "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/infinitetalk-fast/video-to-video-multi" \
  -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