Serverless AI Audio Transcription

Convert speech to text with our advanced audio transcription service. Perfect for transcribing interviews, meetings, lectures, or any audio content. Supports multiple audio formats including MP3, WAV, OGG, and MPEG.

Endpoint

Convert audio recordings to accurate text transcriptions with our AI-powered transcription API.

POSThttps://api.xtartapp.com/audio/transcription

*Authentication

You must use a Bearer token provided by the dashboard to use for authentication. Add the token to the Authorization header.

Request body

NameTypeRequiredMaxDescription
audiostringYes-An optimized audio file to transcribe. Check Audio Upload docs to upload an audio and before using this API.

Response

NameTypeDescription
dataobjectObject containing the transcription results
data.transcriptionstringThe full text transcription of the audio file
data.confidencenumberConfidence score between 0 and 1 indicating the overall transcription accuracy
data.languagestringThe detected language of the audio content
metadataobjectMetadata about the transcription process
metadata.costnumberThe cost of the transcription request

Errors

{
   "error": "string", 
   "code": "string"
}
HTTP StatusError CodeMessage
400INVALID_PAYLOADOccurs when the payload is invalid.
400INVALID_AUDIOOccurs when the audio file format is not supported.
400AUDIO_TRANSCRIPTION_ERRORService is busy, experiencing high demand, or encountered an error processing the audio.
400INSUFFICIENT_BALANCEThe user has insufficient balance.
401UNAUTHORIZEDThe authentication token is invalid or expired.
429TOO_MANY_REQUESTSThe request limit has been reached.