Skip to main content
POST
Extract Transcript

POST /api/v1/transcript

Extract audio-visual transcript from video with word-level timestamps and optional speaker diarization. Returns both structured segments and full text.

Parameters

Response

Transcript Segment Object

Example Request

Example Response

Notes

  • Transcription uses state-of-the-art speech recognition
  • Speaker diarization identifies unique speakers (Speaker 1, Speaker 2, etc.)
  • Timestamps are precise to the hundredth of a second
  • The full_text field provides the complete transcript without timestamps
  • Supports multiple languages (auto-detected)

Body

application/json
video_url
string<uri>
required

URL to the video to transcribe

Example:

"https://example.com/video.mp4"

include_speakers
boolean
default:false

Include speaker diarization

Example:

true

include_timestamps
boolean
default:true

Include word-level timestamps

Example:

true

Response

Transcript extracted successfully

transcript
object[]
required

Array of transcript segments with timestamps

full_text
string
required

Complete transcript as plain text

Example:

"Welcome to the game. Today we have an exciting matchup..."

duration_sec
number
required

Duration of the video in seconds

Example:

3600