Veed Subtitles API Documentation

Veed Subtitles API Documentation

Playground

VEED Subtitles is a fast AI video subtitle generation model that adds styled captions to videos using automatic transcription or supplied SRT files and subtitle content. Ready-to-use REST inference API for subtitled MP4 generation, social media videos, creator content, marketing clips, accessibility workflows, video localization, and professional captioning with simple integration, no coldstarts, and affordable pricing.

Features

VEED Subtitles adds styled subtitles to videos using automatic transcription or an optional SRT subtitle file. Choose subtitle presets, positions, shadow styles, languages, and output resolution tiers.

Why Choose This?

• Automatic transcription
  Upload a video and automatically generate subtitles.

• Optional SRT subtitles
  Upload an SRT file or provide raw SRT content when exact subtitle text and timing are required.

• Multiple subtitle styles
  Choose from standard and dynamic subtitle presets.

• Position and shadow controls
  Adjust subtitle placement and shadow strength for better readability.

• Multiple resolution tiers
  Generate subtitled videos in 480p, 720p, or 1080p.

Parameters

How to Use

1. Upload a video — Select the video you want to subtitle.
2. Choose a resolution — Select 480p, 720p, or 1080p.
3. Choose a preset — Select a standard or dynamic subtitle style.
4. Set position and shadow — Adjust subtitle placement and readability if needed.
5. Choose a language optional — Select a transcription language or leave it empty for automatic detection.
6. Provide subtitles optional — Upload an SRT file or enter raw srt_content.
7. Submit — Generate and download the subtitled video.

Pricing

Pricing depends on input video duration, selected resolution, and whether the selected subtitle preset is standard or dynamic.

Billing Rules

• Base price: $0.11 per input-video minute
• Minimum billed duration: 60 seconds
• Maximum processed and billed duration: 120 seconds
• Duration is rounded up to the next whole second
• 480p and 720p use the base resolution multiplier
• 1080p uses a 2× resolution multiplier
• Dynamic presets use an additional 2× preset multiplier
• Resolution and dynamic-preset multipliers are cumulative
• position, shadow, language, file, and srt_content do not affect pricing

Example Costs

Best Use Cases

• Social media videos — Add styled captions to reels, shorts, and promotional clips.
• Interviews and talking-head videos — Improve accessibility and viewer retention.
• Branded content — Choose subtitle presets that match the visual tone of your content.
• Multilingual content — Select a supported transcription language when automatic detection is not preferred.
• SRT workflows — Burn existing subtitle files or raw SRT content into a video.

Pro Tips

• Leave language empty when you want automatic language detection.
• Use either file or srt_content, not both.
• Use a standard preset for lower-cost subtitle generation.
• Dynamic presets provide more animated styling but cost twice as much as standard presets.
• Selecting 1080p doubles the resolution price.
• Combining 1080p with a dynamic preset results in a 4× total multiplier.
• Videos longer than 120 seconds are processed only up to the first 120 seconds.

Notes

• video is required.
• target_resolution defaults to 720p.
• preset defaults to simple.
• position defaults to bottom.
• shadow defaults to mid.
• The maximum processed video duration is 120 seconds.
• Uploading both file and srt_content in the same request is not supported.

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",
  "target_resolution": "720p",
  "preset": "simple",
  "position": "bottom",
  "shadow": "mid",
  "language": "af-ZA"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/veed/subtitles" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters