Soulx Flashhead

Soulx Flashhead

Playground

SoulX FlashHead enables real-time streaming talking head video generation from portrait image and audio with ultra-fast 96 FPS performance. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

SoulX FlashHead generates realistic talking head videos by combining a portrait image with audio. Upload a face image and audio clip — the model creates a lip-synced video with natural facial movements and expressions. With support for audio clips up to 30 minutes and budget-friendly pricing, it’s ideal for long-form talking avatar content.

Why Choose This?

• Long-form support Generate talking avatar videos with audio up to 30 minutes in length.

• Realistic lip-sync Accurate lip movements synchronized to the audio input.

• Natural expressions Creates realistic facial movements and expressions during speech.

• Budget-friendly Lower cost per second compared to other talking avatar models.

• Resolution options Choose between 480p and 720p output quality.

Parameters

How to Use

1. Upload your image — provide a clear portrait image with visible face.
2. Upload your audio — add the audio clip you want the avatar to speak (up to 30 minutes).
3. Select resolution — choose 720p for higher quality or 480p for faster/cheaper processing.
4. Run — submit and download your talking avatar video.

Pricing

Billing Rules

• Minimum charge: 5 seconds
• Maximum duration: 1800 seconds (30 minutes)
• 480p rate: $0.075 per 5 seconds
• 720p rate: $0.15 per 5 seconds (2× 480p rate)

Best Use Cases

• Long-Form Content — Create extended talking avatar videos for podcasts, lectures, and presentations.
• E-learning — Generate instructor avatars for educational courses and tutorials.
• Digital Presenters — Produce talking avatars for video presentations and explainers.
• Marketing & Ads — Create spokesperson videos without filming.
• Localization — Generate lip-synced videos in different languages from the same avatar.

Pro Tips

• Use clear, front-facing portrait images with good lighting for best results.
• Ensure the face is clearly visible and not obscured by hair or accessories.
• Use high-quality audio with clear speech for accurate lip-sync.
• Choose 480p for longer content to reduce costs — it still provides good quality.
• Set a specific seed for reproducible results across multiple generations.

Notes

• Both image and audio are required fields.
• Maximum audio duration: 30 minutes (1800 seconds).
• Minimum charge: 5 seconds (shorter clips billed as 5 seconds).
• 720p resolution costs 2× the 480p rate.
• Ensure uploaded file URLs are publicly accessible.

Related Models

• SkyReels V3 Talking Avatar — Higher quality for short clips (up to 15s).
• DreamActor V2 — Motion transfer from driving video to character image.
• Wan 2.6 Image-to-Video — General image-to-video generation.

Duration limit

The maximum supported audio duration is 10 minutes. Longer audio is automatically trimmed to 10 minutes before processing.

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'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "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/soulx-flashhead" \
  -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