Quickstart

Get an API key

export AIRCAPS_API_KEY="aircaps_sk_..."

Submit audio

Pass a URL the API can download (public or presigned):

curl https://api.aircaps.com/v1/transcripts \
  -H "Authorization: Bearer $AIRCAPS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "a5s-async-v1", "audio_url": "https://example.com/meeting.mp3", "language_code": "en"}'

language_code is optional (default en).The response is a transcript object with "status": "queued" or "processing" and an id like tr_01k6z....

Get the result

curl https://api.aircaps.com/v1/transcripts/tr_01k6z... \
  -H "Authorization: Bearer $AIRCAPS_API_KEY"

Poll until status is completed (or error), or pass a webhook_url when you submit to be notified instead.

Local files in Python

# pip install requests
import os, sys, time, requests

API = "https://api.aircaps.com/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['AIRCAPS_API_KEY']}"}

# 1. Upload straight to storage
upload = requests.post(f"{API}/files/upload-url", headers=HEADERS).json()
with open(sys.argv[1], "rb") as f:
    requests.put(upload["upload_url"], data=f).raise_for_status()

# 2. Transcribe
job = requests.post(f"{API}/transcripts", headers=HEADERS,
                    json={"model": "a5s-async-v1", "file_id": upload["id"], "language_code": "en"}).json()

# 3. Wait for the result
while job["status"] in ("queued", "processing"):
    time.sleep(3)
    job = requests.get(f"{API}/transcripts/{job['id']}", headers=HEADERS).json()

for u in job["utterances"]:
    print(f"[{u['start']:7.1f}s] {u['speaker']}: {u['text']}")

Language: both models transcribe English only today. Pass language_code (batch) or language (streaming) as en or a regional variant such as en-US or en-GB. Any other value returns unsupported_language. Multilingual support is planned and will be available soon.

Next: batch transcription in depth or live streaming.

Get started

Guides

Operations

Local files in Python

​Local files in Python

Local files in Python