Bytedance Avatar Omni Human

Bytedance Avatar Omni Human

Playground

OmniHuman turns a single portrait photo into avatar video with lifelike motion and expressions ($0.12/sec). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Transform any portrait into a realistic talking avatar with Avatar Omni Human. Simply upload a photo and an audio clip, and watch the subject come to life with perfectly synchronized lip movements, natural expressions, and lifelike head motion — ideal for virtual presenters, digital content, and personalized video messages.

Why It Looks Great

• Realistic lip sync: Advanced audio analysis ensures precise mouth movements matching every syllable.
• Natural expressions: Generates authentic facial expressions and subtle head movements.
• Simple workflow: Just two inputs — an image and audio — for complete avatar generation.
• High fidelity: Preserves the original portrait’s likeness and quality.
• Versatile audio support: Works with speech, singing, and various audio types.

Parameters

How to Use

1. Upload your image — drag and drop a clear portrait photo or paste a public URL.
2. Upload your audio — add the speech or audio you want the avatar to perform.
3. Run — click the button to generate.
4. Download — preview and save your talking avatar video.

Pricing

Per-second billing based on audio duration.

Examples

Best Use Cases

• Virtual Presenters — Create AI spokespeople for videos, presentations, and training content.
• Personalized Messages — Generate custom video messages from a single photo.
• Content Localization — Dub content into different languages with matching lip movements.
• Social Media Content — Produce engaging talking-head videos without filming.
• E-learning & Training — Create instructor-led content from static presenter images.
• Digital Avatars — Bring character portraits and illustrations to life with speech.

Pro Tips for Best Results

• Use clear, front-facing portrait photos with good lighting for best lip sync accuracy.
• Ensure the face is clearly visible and not obscured by hair, accessories, or shadows.
• High-quality audio with minimal background noise produces more accurate synchronization.
• Neutral or slightly open mouth expressions in the source image work best.
• The subject’s face should be a reasonable size in the frame — not too small or cropped.
• Test with shorter audio clips first before processing longer content.

Notes

• If using URLs for image or audio, ensure they are publicly accessible.
• The enable_base64_output option is only available through the API.
• Processing time scales with audio duration.
• Best results come from portrait-style images with clear facial features.
• Works with various audio formats — speech, narration, singing, and more.

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"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/avatar-omni-human" \
  -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