Image Text Remover API Documentation

Image Text Remover API Documentation

Playground

AI Image Text Remover that erases on-image text cleanly and reconstructs the background with stunning visual accuracy. Automatically removes captions, labels, subtitles, watermarks, annotations, or embedded UI text while preserving texture, lighting, and scene integrity. Ready-to-use REST inference API, fast performance, no coldstarts, and affordable pricing.

Features

Remove unwanted text from any image with pixel-level reconstruction. WaveSpeedAI Image Text Remover automatically finds text regions and rebuilds the underlying background so the edit looks natural — no blurry blocks, no jagged edges.

What is it?

WaveSpeedAI Image Text Remover is an end-to-end image cleanup tool:

• Input: an image containing text (captions, labels, subtitles, UI text, stickers, overlays)
• Output: a clean image with the text removed and background filled in
• Workflow: text detection → intelligent mask generation → background inpainting

It’s designed for cleaning social posts, product photos, posters, screenshots, UI/UX mockups, marketing materials, and any image you want to reuse without visible text.

Why it stands out

• High-fidelity inpainting Reconstructs texture, lighting, depth, and structure to blend the edited area into the original scene with minimal artifacts.

• Fully automatic workflow Just upload your image and run the model—no need for manual masking, brushing, or Photoshop skills.

• Text-focused cleanup Works especially well on captions, subtitles, labels, annotations, and embedded UI strings; also effective on many watermarks and overlays.

• Flexible output formats Choose JPEG, PNG, or WEBP so the result fits directly into your web, app, or design pipeline.

• Batch and API friendly Suitable for e-commerce asset cleanup, marketing automation, dataset preparation, and production-scale image processing.

Limits and performance

• Input formats: JPEG, PNG, WEBP
• Output formats: JPEG / PNG / WEBP (selectable)
• Typical processing time: a few seconds per image, depending on resolution and queue load
• Best cases: clearly readable text that is not extremely stylized or heavily blended into complex textures

Pricing

• Each processed image costs $0.15.

How to use

1. Upload an image or paste a publicly accessible image URL.
2. Choose your preferred output_format (JPEG, PNG, or WEBP).
3. Click run to start automatic text detection and removal.
4. Download your cleaned, text-free image from the result panel or dashboard.

Pro tips for best quality

• Use the highest-resolution version of the image you have; more pixels mean better inpainting.
• Flat or simple backgrounds are easiest to reconstruct; complex patterns may occasionally need light manual touch-up.
• For semi-transparent watermarks or overlays, higher resolution and good contrast between text and background improve results.

Notes

• If you provide an image URL instead of uploading, make sure it is publicly accessible; a valid image will show a preview before you run the job.
• Extremely stylized, warped, or deeply textured text may not be removed perfectly in one pass.

Related tools

• WaveSpeedAI Image Translator: Translate on-image text into 30+ languages while preserving layout.
• WaveSpeedAI Image Eraser: General-purpose object removal and background reconstruction for non-text elements.

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",
  "output_format": "jpeg"
}
JSON
)

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