Molmo2 Video Captioner API Documentation

Molmo2 Video Captioner API Documentation

Playground

Molmo2-4B Video Captioner: Generate detailed, accurate captions for videos with customizable detail levels (low, medium, high). Open-source vision-language model with temporal understanding capabilities. Ready-to-use REST API, no cold starts, duration-based pricing.

Features

Molmo2 Video Captioner is an intelligent video understanding model that generates detailed captions and descriptions for video content. Upload a video and receive natural-language descriptions of scenes, actions, objects, and events — with adjustable detail levels to match your workflow needs.

Perfect for content creators, accessibility teams, and developers building video understanding pipelines.

Why Choose This?

• Adjustable detail levels Choose from low, medium, or high detail to control caption depth — from quick summaries to comprehensive scene breakdowns.

• Scene-aware captioning Understands context, actions, objects, environments, and temporal flow to produce coherent, meaningful descriptions.

• Flexible video input Accepts video uploads or public URLs for seamless integration into existing workflows.

• Fast processing Optimized for quick turnaround while maintaining caption accuracy and coherence.

• Production-ready API Ready-to-use REST endpoint with predictable per-second pricing and no cold starts.

Parameters

Detail Level Options

• Low — Brief, high-level summary of the video content
• Medium — Balanced description with key scenes and actions (default)
• High — Comprehensive breakdown with fine-grained details

How to Use

1. Upload your video — drag and drop a file or paste a public video URL.
2. Select detail level — choose low, medium, or high based on your needs.
3. Submit — the model processes the video and returns a caption.
4. Use the output — integrate captions into your content, accessibility tools, or data pipelines.

Pricing

Per-5-second billing with a 5-second minimum.

Billing Rules

• Minimum charge: 5 seconds ($0.005)
• Rate: $0.001 per second ($0.005 per 5 seconds)
• Maximum video length: 120 seconds (2 minutes)

Best Use Cases

• Accessibility — Generate video descriptions for visually impaired users and screen readers.
• Content indexing — Create searchable metadata for video libraries and archives.
• Social media — Auto-generate captions for posts, reels, and stories.
• Video SEO — Improve discoverability with rich text descriptions for video content.
• Surveillance and monitoring — Summarize footage for quick review and logging.
• Education — Describe instructional videos for enhanced learning materials.

Notes

• If using a URL, ensure it is publicly accessible. A preview thumbnail in the interface confirms successful access.
• For videos longer than 2 minutes, split into segments and process separately.
• Clear, well-lit footage yields the most accurate captions.
• Use high detail level for complex scenes; low detail for quick overviews.

Duration limit

The maximum supported video duration is 2 minutes.

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",
  "detail_level": "medium"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/video-captioner" \
  -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