Skip to main content
GET
/
video
/
{video_id}
/
transcription
Get video transcription
curl --request GET \
  --url https://api.videodb.io/video/{video_id}/transcription/ \
  --header 'x-access-token: <api-key>'
{
  "success": true,
  "status": "completed",
  "data": {
    "transcript": [
      {
        "text": "Hello world",
        "start": 1.5,
        "end": 3.2
      }
    ]
  }
}
Retrieve the timestamped transcription for a video. Supports multiple segmentation types and time ranges. 
import videodb

conn = videodb.connect(api_key="your_api_key")
coll = conn.get_collection()
video = coll.get_videos()[0]

# Get full transcript with word-level timestamps
transcript = video.get_transcript()

for segment in transcript:
    print(f"{segment['start']:.2f}s - {segment['text']}")

# Get plain text transcript
text = video.get_transcript_text()
print(f"Full text: {text}")
  • Returns timestamped transcript with start, end, and text for each segment
  • Segmentation supports: word (default), sentence, and time-based
  • Can retrieve partial transcripts using start/end time parameters (in seconds)
  • Generates transcript if not already created
  • Use force: true to regenerate transcript instead of returning cached version

Authorizations

​
x-access-token
string
header
required

API key for authentication (sk-xxx format)

Path Parameters

​
video_id
string
required
Example:

"m-12345"

Query Parameters

​
engine
string
default:default
Example:

"default"

​
start
number
default:0
Example:

10.5

​
end
number
default:-1
Example:

60

​
segmenter
string
default:word
Example:

"word"

​
length
integer
default:1
Example:

1

Response

200 - application/json

Transcription data

​
success
boolean
Example:

true

​
status
enum<string>
Available options:
completed,
processing,
failed
Example:

"completed"

​
data
object