$ man video-transcribe
/video-transcribe(1)
NAME
video-transcribe — transcribe video / video transcription / video to audio transcription / video-to-text
synonym alias of video-to-text — reuses the canonical handler.
SYNOPSIS
POST https://x402.org/v1/video-transcribe
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Transcribe video / video transcription / video to audio transcription / video-to-text. Whisper v3 large transcription for any video URL. Auto-detects 90+ languages. Translate-to-English mode. 60-min / 500MB max. Speaker diarization optional. Same backend as video-to-text under a clearer slug.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| media_url | string | Public URL of an audio or video file. Supports mp3, mp4, mpeg, mpga, m4a, wav, webm. Max 60 minutes. | required |
| language | string | Optional ISO language code (e.g. 'en', 'fr', 'es'). If omitted, auto-detected. | optional |
| task | string | Either 'transcribe' (default) or 'translate' (translates to English). enum: transcribe · translate | optional |
| diarize | boolean | Whether to identify different speakers. Default false. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| text | string | Full transcript text |
| chunks | array | Time-segmented chunks with timestamps |
| detected_languages | array | Languages auto-detected in the audio |
| duration_seconds | number | Source media duration in seconds |
| task | string | Echo of the task performed |
| source_url | string | Echo of the input URL |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.org/v1/video-transcribe \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# install once claude mcp add x402 --command "npx x402-deployer-mcp" # then ask Claude Code: # "use the video-transcribe tool to ..."
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- transcribevideoaudiowhispertranscription
- methods
- POST
- cluster
- mediakit
- price
- $0.10 USDC per call
ADJACENT — other endpoints in mediakit
| endpoint | description | price |
|---|---|---|
| extract-tables | Extract tables from PDF / table extractor / PDF to CSV / spreadsheet from PDF. | $0.10 |
| mp4-to-mp3 | MP4 → MP3 audio extractor. | $0.10 |
| pdf-extract-tables | PDF table extractor / table from PDF / scanned-table parsing / financial-table OCR / multi-page table consolidator / Datalab Marker tables. | $0.10 |
| pdf-to-jpg | PDF to JPG / PNG / WEBP image converter. | $0.10 |
| speaker-diarize | Speaker diarization / who-said-what transcription. | $0.10 |
| transcribe | Video / audio transcription via Whisper v3. | $0.10 |
| upscale-image | AI image upscaler / super-resolution / image enlarger. | $0.10 |
| video-summarize | Video summarizer / podcast summarizer / lecture notes generator. | $0.10 |
SEE ALSO