agentutility(7)$ man video-summarize
/video-summarize
NAME
video-summarize — summarizes videos, podcasts, and lectures in one call: whisper v3 transcribes, then mistral summarizes
SYNOPSIS
POST https://x402.agentutility.ai/video-summarize
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Summarizes videos, podcasts, and lectures in one call: Whisper v3 transcribes, then Mistral summarizes. 5 styles (tldr, bullets, paragraph, executive, chapters); returns summary + transcript; 60 min max. Use it as a video summarizer, podcast summarizer, or lecture notes generator.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| media_url | string | URL of the video/audio file to transcribe and summarize. | required |
| style | string | Summary format: tldr, bullets, paragraph, executive, or chapters. Optional, default bullets. enum: tldr · bullets · paragraph · executive · chapters | optional |
| max_words | number | Target word count for the summary. Optional, 1-1000. | optional |
| language | string | Source language hint passed to Whisper (ISO code). Optional, auto-detected if omitted. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| summary | string | Generated summary text in the requested style. |
| style | string | Summary style actually used (echoes the input style parameter). |
| transcript | string | Full Whisper v3 transcript of the source media. |
| transcript_chars | number | Character count of the returned transcript. |
| duration_seconds | number | Length of the source media in seconds. |
| detected_languages | array | Languages Whisper detected in the audio, as ISO codes. |
| summary_model | string | Mistral model identifier used to write the summary. |
| transcribe_model | string | Whisper model identifier used for transcription (v3). |
| source_url | string | Echo of the media_url that was transcribed. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/video-summarize \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# Install the MCP package for this endpoint's cluster npx -y @agentutility/mcp-<cluster> # Required: EVM private key with USDC on Base export X402_PRIVATE_KEY=0x... # Then call the video-summarize tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- videopodcastsummarizetranscribewhisper
- env
- FAL_KEY_TRANSCRIBE · VENICE_API_KEY
- methods
- POST
- cluster
- mediakit
- price
- $0.10 USDC per call
ADJACENT — other endpoints in mediakit
| endpoint | description | price |
|---|---|---|
| doc-to-json | Converts any document (PDF, DOCX, PPT, XLSX, or image) into structured JSON matching a caller-supplied schema. | $0.10 |
| extract-tables | Detects and extracts every table from a PDF document, returning structured JSON or CSV per table. | $0.10 |
| pdf-extract-tables | Extracts every table from a PDF, digital or scanned, and returns row-by-column text matrices page-by-page. | $0.10 |
| pdf-table-extract | Extracts tables from digital or scanned PDFs, returning row/column matrices, CSV output, page numbers, and optional cell boxes. | $0.10 |
| pdf-table-extractor | Finds tables in digital or scanned PDFs and returns row-by-column matrices, page numbers, and optional cell bounding boxes. | $0.10 |
| pdf-to-jpg | Convert a PDF into page images for previews, thumbnails, or archiving. | $0.10 |
| speaker-diarize | Transcribe audio or video and label who said what. | $0.10 |
| transcribe | Convert spoken audio or video into text. | $0.10 |
SEE ALSO