Transcription
Transcribe an audio file
Send an audio file and receive the transcript in the same HTTP request/response cycle — no webhooks or polling required. Optionally, the endpoint can also label who spoke when (diarisation) and detect music such as hold tones.
Supported audio formats: WAV, MP3, FLAC, AAC, OGG, MP4, AIFF, OPUS.
Processing may take up to 2min30s, or fail altogether, on long, low-quality, or complex audio. Keep clips short where you can.
query Parameters
lang_codeLanguage code for transcription. If not specified, the language is auto-detected. Supported codes: afr (Afrikaans), zul (isiZulu), sot (Sesotho), eng (South African English), fra (African French). See Language Support for the current status of every language.
Language code for transcription. If not specified, the language is auto-detected. Supported codes: afr (Afrikaans), zul (isiZulu), sot (Sesotho), eng (South African English), fra (African French). See Language Support for the current status of every language.
diariseLabel segments and words with speaker IDs.
Label segments and words with speaker IDs.
detect_musicDetect music, such as music-on-hold.
Detect music, such as music-on-hold.
translateTranslate the transcript.
Translate the transcript.
Transcribe an audio file › Request Body
fileThe audio file to transcribe. Supported formats: WAV, MP3, FLAC, AAC, OGG, MP4, AIFF, OPUS.
Transcribe an audio file › Responses
Successful Response
Unique identifier for this transcription.
Duration of the submitted audio, in seconds.
The language used — either your lang_code or the auto-detected language.
Present when diarise=1: a timeline of silence/speech/music segments with speaker IDs and text, plus per-word timings and confidence in words.
The full transcript.
COMPLETED on success.
Populated when transcription fails.