framefetch

{'type': 'object', 'properties': {}}

{'type': 'object', 'required': ['url'], 'properties': {'ask': {'type': 'string', 'maxLength': 500, 'minLength': 3, 'description': 'Question about the video (3-500 chars); <=500-token answer w/ timestamped quotes, grounded in the transcript (auto-pulled). Never cached; degrades (never charged) if unavailable. Long videos: answer draws on a relevance-selected/sampled subset, not just the head â\x80\x94 see response `ask.coverage`. No transcript (e.g. Pinterest): falls back to frames, `based_on`:["frames"].'}, 'url': {'type': 'string', 'description': 'Public video URL from a supported platform.'}, 'cache': {'type': 'boolean', 'description': 'false forces a fresh, billed extract.'}, 'voice': {'enum': ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer', 'Fritz-PlayAI'], 'type': 'string', 'description': 'Voice for "audio_digest": OpenAI voices (alloy/echo/fable/onyx/nova/shimmer) + Groq "Fritz-PlayAI"; default "alloy".'}, 'fields': {'type': 'array', 'items': {'enum': ['metadata', 'insights', 'transcript', 'frames', 'text_overlay', 'digest', 'audio_digest', 'structured', 'comments', 'comment_sentiment', 'delta'], 'type': 'string'}, 'description': 'Which data to return; default ["metadata"]. Pulls: digestâ\x86\x92transcript; audio_digestâ\x86\x92digestâ\x86\x92transcript; structuredâ\x86\x92transcript; comment_sentimentâ\x86\x92comments. digest/audio_digest/structured/comment_sentiment: degrade to a warning, never charged, on failure. digest: gist+topics via LLM. audio_digest: mp3 of digest (signed URL, 24h); voice via `voice`; +`translate` for other-language audio. structured: chapters/entities/products_shown/claims/key_moments via vision LLM. comments: up to comments_cap; YouTube only (else warning; see GET /v1/platforms). comment_sentiment: aggregated audience sentiment (positive_pct/neutral_pct/negative_pct/summary/top_themes); needs >=5 comments; same YouTube-only limit. text_overlay: OCR per frame; requires "frames"; skipped above 200 frames. delta: velocity vs the previous fetch; first call seeds the baseline. Docs: https://framefetch.net/docs.'}, 'frames': {'type': 'object', 'required': ['mode'], 'properties': {'n': {'type': 'number', 'description': 'every_n: take every Nth source frame'}, 'to': {'type': 'number', 'description': 'range: end second'}, 'fps': {'type': 'number', 'description': 'fps/range: frames per second (max 60)'}, 'from': {'type': 'number', 'description': 'range: start second'}, 'mode': {'enum': ['all', 'every_n', 'fps', 'range'], 'type': 'string'}, 'width': {'type': 'number', 'description': 'downscale width in px (16â\x80\x937680)'}, 'format': {'enum': ['jpg', 'png', 'webp'], 'type': 'string'}}, 'description': 'Frame-sampling spec; required when "frames" or "text_overlay" is requested.'}, 'translate': {'type': 'string', 'description': 'ISO-639-1 target language (e.g. "es"); adds `transcript_translated` (timings kept). Requires "transcript" (or "digest"). Billed per audio-minute.'}, 'comments_cap': {'type': 'integer', 'maximum': 200, 'minimum': 1, 'description': 'Max top-level comments (1-200, default 30); only used with "comments".'}, 'subtitle_format': {'enum': ['srt', 'vtt'], 'type': 'string', 'description': 'Renders transcript as subtitles in `subtitles` (srt/vtt). Requires "transcript" (or "digest"); uses translated cues if "translate" set.'}}}

{'type': 'object', 'properties': {}}

{'type': 'object', 'required': ['query'], 'properties': {'cache': {'type': 'boolean', 'description': 'false = fresh, billed search.'}, 'limit': {'type': 'integer', 'maximum': 25, 'minimum': 1, 'description': 'Default 10.'}, 'query': {'type': 'string', 'description': '2-200 chars.'}, 'platform': {'enum': ['youtube'], 'type': 'string'}}}