intelligence

Audio transcription

6 credits per minute. Speaker labels, word timestamps, language auto-detect.

6 credits

Billing: Per minute
Implementation: Computed in Klaris
GDPR: Ordinary data
Request fields: urlexpected_duration_minutes

POST /api/v1/audio-transcription

curl

curl -X POST "$KLARIS_URL/api/v1/audio-transcription" \
  -H "Authorization: Bearer $KLARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://example.com",
  "expected_duration_minutes": "5"
}'

JavaScript

const payload = {
  url: "https://example.com",
  expected_duration_minutes: "5",
};

const res = await fetch(`${process.env.KLARIS_URL}/api/v1/audio-transcription`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.KLARIS_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify(payload),
});

Python

import os
import requests

payload = {
    "url": "https://example.com",
    "expected_duration_minutes": "5"
}

requests.post(
    f"{os.environ['KLARIS_URL']}/api/v1/audio-transcription",
    headers={"Authorization": f"Bearer {os.environ['KLARIS_API_KEY']}"},
    json=payload,
)

Set KLARIS_URL to your Klaris origin and KLARIS_API_KEY to a live key.

All products →