Image Text Remover API Documentation

Image Text Remover API Documentation

Playground

Try it on WaveSpeedAI!

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.

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 once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -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}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-The URL of the image to generate an image from.
output_formatstringNojpegjpeg, png, webpThe format of the output image.

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.