Skip to content

Askara SpeechToText API (2.0.0)

Askara.ai SpeechToText API

Languages
Servers
Production

https://stt.askara.ai/v2/

Transcribe an audio file.

Request

Use this endpoint to extract text speech from an audio file.

Security
bearerAuth
Bodyapplication/jsonrequired

The new Patient resource

idstringrequired

Identifier of the audio in your application.

Example: "identifier"
urlstring(uri)required

URL of the audio file. It should be available without any authentication.

Example: "https://askara-bucket.s3.eu-west-3.amazonaws.com/test/audio.webm"
callbackUrlstring(uri)required

Callback URL to be called after the audio transcription is finished.

Example: "https://api.askara.ai/webhook/stt"
curl -i -X POST \
  https://stt.askara.ai/v2/transcription \
  -H 'Content-Type: application/json' \
  -H 'X-API-KEY: YOUR_API_KEY_HERE' \
  -d '{
    "id": "identifier",
    "url": "https://askara-bucket.s3.eu-west-3.amazonaws.com/test/audio.webm",
    "callbackUrl": "https://api.askara.ai/webhook/stt"
  }'

Responses

Audio transcription

Bodyapplication/jsonArray [
idstringrequired

Identifier of the audio in your application.

Example: "identifier"
urlstring(uri)required

URL of the audio file. It should be available without any authentication.

Example: "https://askara-bucket.s3.eu-west-3.amazonaws.com/test/audio.webm"
transcriptionstring(uri)required

Text transcription of the audio file.

Example: "Adresser le patient pour extraire les 2 dents"
]
Response
application/json
[
  {
    "id": "identifier",
    "url": "https://askara-bucket.s3.eu-west-3.amazonaws.com/test/audio.webm",
    "transcription": "Adresser le patient pour extraire les 2 dents"
  }
]