Skip to content
clusters: prooflayer · edgemarket · edgefinance · synthforge · mediakit · wordmint · webprobe · locale · comppoint · rollforge · bestiary · statline · matchpoint · retail · agentops · browserworkflow · modelrouter · compose
$ man subtitles

/subtitles

agentutility / mediakit / subtitles
PRICE / CALL
$0.08
USDC · base mainnet · scheme: exact
METHOD
POST
CLUSTER
mediakit
CATEGORY
media
STATUS
live
NAME
subtitles srt / vtt subtitle generator from video or audio
SYNOPSIS
POST https://x402.agentutility.ai/subtitles
     Content-Type: application/json
     X-PAYMENT:    <signed-transferWithAuthorization>

     { ... }
↳ first call → 402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.
DESCRIPTION

SRT / VTT subtitle generator from video or audio. Whisper v3. Word-wrapped, ready for VLC / Premiere / FFmpeg.

INPUTrequest schema
propertytypedescriptionreq?
media_urlstringrequired
formatstringoptional
languagestringoptional
taskstringoptional
max_chars_per_linenumberoptional
OUTPUTresponse shape
fieldtypedescription
subtitlesstringFull subtitle file content as a string.
formatstringEcho of the format used.
mime_typestringMIME type for the subtitle format ('application/x-subrip' or 'text/vtt').
cue_countnumberNumber of subtitle cues generated.
duration_secondsnumberSource media duration.
detected_languagesarrayLanguages auto-detected in the audio.
taskstringEcho of the task performed.
source_urlstringEcho of the input URL.
EXAMPLEStwo ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/subtitles \
  -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 subtitles tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
tags
subtitlessrtvttcaptionswhispertranscription
env
FAL_KEY_TRANSCRIBE
methods
POST
cluster
mediakit
price
$0.08 USDC per call
ADJACENTother endpoints in mediakit
endpointdescriptionprice
html-to-pdfConverts a URL to PDF with CloudConvert capture-website; renders JS.$0.08
doc-to-jsonConverts any document (PDF, DOCX, PPT, XLSX, or image) into structured JSON matching a caller-supplied schema.$0.10
extract-tablesDetects and extracts every table from a PDF document, returning structured JSON or CSV per table.$0.10
pdf-extract-tablesExtracts every table from a PDF, digital or scanned, and returns row-by-column text matrices page-by-page.$0.10
pdf-table-extractExtracts tables from digital or scanned PDFs, returning row/column matrices, CSV output, page numbers, and optional cell boxes.$0.10
pdf-table-extractorFinds tables in digital or scanned PDFs and returns row-by-column matrices, page numbers, and optional cell bounding boxes.$0.10
pdf-to-jpgConverts a PDF to JPG, PNG, or WEBP images, rendering every page at configurable DPI (36-600) and returning one image URL per page.$0.10
speaker-diarizeSpeaker diarization / who-said-what transcription.$0.10
SEE ALSO
agentutility · mediakit · x402 · mcp · llms.txt · registry.json · bazaar.x402.org