Get started

Quickstart

Transcribe one file with POST /v1/speech-to-text.

  1. Create an API key.
  2. Send model, then the audio as file. params is an optional JSON string.
  3. The call stays open for up to 4 minutes. When the job is still queued or running, read GET /v1/speech-to-text/{job_id}.
curl https://api.pascalai.co/v1/speech-to-text \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F model=whisper-large-v3-turbo \
  -F params='{"language":"en"}' \
  -F file=@meeting.wav

curl https://api.pascalai.co/v1/speech-to-text/$JOB_ID \
  -H "Authorization: Bearer $PASCAL_API_KEY"

A folder of files is POST /v1/speech-to-text/batch. See Speech to text.