LLM / Multimodal

molmo2-video-captioner (balanced)

Generate detailed captions from a video with temporal actions, scene changes, objects, and visual context. Input: video_url and detail_level (low, medium, or high). Output: text caption. Use for: video captioning, accessibility descriptions, content summaries, and visual QA.

post/api/v1/molmo2-video-captioner

Request

  • Base URL: https://api.muapi.ai
  • URL: https://api.muapi.ai/api/v1/molmo2-video-captioner
  • Auth: one of:
    • API key in header x-api-key
    • OAuth 2 (client credentials, token URL https://api.muapi.ai/oauth/token)

Query parameters

webhookstring
team_idinteger nullable

Headers

x-api-keystring
x-embed-codestring nullable
x-agent-embed-codestring nullable
x-whitelabel-studiostring nullable
authorizationstring nullable

Request body

video_urlstring uri required
detail_level'low' | 'medium' | 'high'
webhook_urlstring uri nullable

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 2 revisions of this API.