Skip to main content

Audio Transcription

Convert spoken audio into text using a Whisper model. Use this for meeting transcription, voice command parsing, subtitle generation, or any speech-to-text workflow.

POST 
/v1/audio/transcriptions

Transcribe speech from an audio file to text using a Whisper model. Upload the audio as multipart/form-data.

Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm

curl -X POST https://inference.wiline.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $WEC_API_KEY" \
  -F "[email protected];type=audio/mpeg" \
  -F "model=whisper-1"

Request​

Responses​

Successful Response