Skip to main content
POST
/
audio
/
transcribe
Transcribe Audio
curl --request POST \
  --url https://api.munsit.com/api/v1/audio/transcribe \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-api-key: <api-key>' \
  --form file='@example-file' \
  --form model=munsit

​
Endpoint

POST /audio/transcribe

​
Authentication

Use API key authentication: 
x-api-key: YOUR_MUNSIT_API_KEY

​
Request

multipart/form-data
FieldTypeRequiredDescription
filefileYesAudio file in a supported format
modelstringNoASR model to use: munsit (default) or munsit-en-ar (mixed Arabic-English with code-switching)

​
Response

FieldTypeDescription
transcriptionIdnumberTranscription identifier
transcriptionstringFull transcript text
durationnumberAudio duration in seconds
timestampsarray of objects (word, start, end)Word-level timestamps

Authorizations

​
x-api-key
string
header
required

API key for authentication

Body

multipart/form-data
​
file
file
required

Audio file to transcribe

​
model
enum<string>
default:munsit

ASR model to use. Defaults to munsit.

Available options:
munsit,
munsit-en-ar

Response

Transcription created successfully