Transcription workflow

1

Upload your file

This step is optionnal if you are already working with audio URLs.

If you’re working with audio or video files, you’ll need to upload it first using our /upload endpoint with multipart/form-data content-type since Gladia /v2/transcription endpoint only accept audio URLs.

If you are already using audio file URLs, proceed to the next step.

curl --request POST \
  --url https://api.gladia.io/v2/upload \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-gladia-key: YOUR_GLADIA_API_TOKEN' \
  --form audio=@/path/to/your/audio/conversation.wav

Example response :

{
  "audio_url": "https://api.gladia.io/file/636c70f6-92c1-4026-a8b6-0dfe3ecf826f",
  "audio_metadata": {
    "id": "636c70f6-92c1-4026-a8b6-0dfe3ecf826f",
    "filename": "conversation.wav",
    "extension": "wav",
    "size": 99515383,
    "audio_duration": 4146.468542,
    "number_of_channels": 2
  }
}

We will now proceed to the next steps using the returned audio_url.

2

Transcribe

We’ll now POST the transcription request to Gladia’s API using the /v2/transcription endpoint.

/v2/transcription only accept application/json as Content-Type.

  curl --request POST \
    --url https://api.gladia.io/v2/transcription \
    --header 'Content-Type: application/json' \
    --header 'x-gladia-key: YOUR_GLADIA_API_TOKEN' \
    --data '{
    "audio_url": "YOUR_AUDIO_URL",
    "diarization": true,
    "diarization_config": {
      "number_of_speakers": 3,
      "min_speakers": 1,
      "max_speakers": 5
    },
    "translation": true,
    "translation_config": {
      "model": "base",
      "target_languages": ["fr", "en"]
    },
    "subtitles": true,
    "subtitles_config": {
      "formats": ["srt", "vtt"]
    },
    "detect_language": true,
    "enable_code_switching": false
    }
  '

You’ll get an instant response from the request with and id and a result_url. The id is your transcription ID that you will use to get your transcription result once it’s done.

result_url is returned for convenience. This is a pre-built url with your transcription id in it that you can use to get your result in the next step.

3

Get the transcription result

You can get your transcription results in 3 different ways:

Callback are HTTP calls that you can use to get notified when your transcripts are ready.

Instead of polling and keeping your server busy and maintaining work, you can use the callback_url feature. By providing a callback_url on your transcription request body payload, we will send the results right there once your transcription is done.

{
  "audio_url": "YOUR_AUDIO_URL",
  "callback_url": "https://yourserverurl.com/your/callback/endpoint/"
}

Once the transcription is done, a POST request will be made to the callback_url you provided.
The request body is a JSON object containing the transcription id and an event property that tells you if it’s a success or an error.

API Documentation

Transcription

Upload

Webhooks

Callback