Content Studio

Transcription

Turn speech in an audio recording into text, with a downloadable transcript.

audio.transcribe converts speech in an MP3 or WAV recording into text. Upload the file with POST /v1/uploads, create the job, then read the transcript from the result or download it as JSON or plain text.

OperationInputCreditsResult files
audio.transcribeMP3 or WAV, up to 100 MB1 credit per minutetranscript_json, transcript_txt, plus text

Input

uploadIdstringrequired

Upload of an MP3 or WAV file.

languagestringoptionaldefault: auto

Spoken language as an ISO 639-1 code (for example hi, en, ta) or a language name. Omit or pass auto to detect it.

keytermsstring[]optional

Up to 100 names or terms to bias recognition toward.

Code Example

curl -X POST https://api.transpera.io/v1/jobs \
  -H "authorization: Bearer tp_test_..." \
  -H "content-type: application/json" \
  -H "idempotency-key: $(uuidgen)" \
  -d '{
    "operation": "audio.transcribe",
    "input": {"uploadId": "UPLOAD_ID", "language": "hi"}
  }'

Result

Result of a finished audio.transcribe job
{
  "job": {
    "id": "JOB_ID",
    "operation": "audio.transcribe",
    "status": "succeeded",
    "chargedCredits": 3,
    "result": {
      "type": "files",
      "text": "Namaste, welcome to the call...",
      "files": [
        {
          "role": "transcript_json",
          "fileName": "transcript.json",
          "url": "https://...",
          "expiresAt": "..."
        },
        {
          "role": "transcript_txt",
          "fileName": "transcript.txt",
          "url": "https://...",
          "expiresAt": "..."
        }
      ]
    }
  }
}