Transcribe an audio file

Every references, assumptions, and commands mentioning “audio files” are also true & works for video files.

🤖 Using your terminal with cURL command

If you are a developer, you probably want to check our API Documentation.

You’ll need:

Your local audio file (referred as YOUR_LOCAL_AUDIO_FILE in the below example)
Your Gladia API key (referred as YOUR_GLADIA_API_TOKEN in the below example)

First, we need to upload your local file to Gladia API :

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

If your upload succeeded, you’ll get a response of type :

{
  "audio_url":"https://api.gladia.io/file/43a853cf-990e-43c3-8c5d-594c0b2bfc95",
  "audio_metadata":
    {
      "id":"43a853cf-990e-43c3-8c5d-594c0b2bfc95",
      "filename": "conversation.wav",
      "extension": "wav",
      "size": 1813648,
      "audio_duration": 26.555465,
      "nb_channels": 2
    }
}

audio_url : The audio URL we’ll use to send the transcription request
audio_metadata : Metadata we got from your audio files

Now that you have an audio link, you can proceed with the “Transcribe audio links” part 👇👇👇

You’ll need:

Your audio link URL (referred as YOUR_AUDIO_LINK_URL in the below example)
Your Gladia API key (referred as YOUR_GLADIA_API_TOKEN in the below example)

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_LINK_URL"
  }'

If your transcription request is accepted, you’ll get a response of type :

{
  "id": "40aae358-6bfd-4c01-bf1d-0fc7c0f02707",
  "result_url": "https://api.gladia.io/v2/transcription/40aae358-6bfd-4c01-bf1d-0fc7c0f02707"
}

id : Your transcription ID
result_url : A pre-built URL for convenience to fetch your result

At this stage, your transcription is queued and will be processed shortly. To check its status and/or get its result, use the result_url we provided you:

curl --request GET \
  --url https://api.gladia.io/v2/transcription/40aae358-6bfd-4c01-bf1d-0fc7c0f02707 \
  --header 'x-gladia-key: YOUR_GLADIA_API_TOKEN'

You should get a JSON response like this :

{
  "id": "40aae358-6bfd-4c01-bf1d-0fc7c0f02707",
  "request_id": "G-99eaeae8",
  "kind": "pre-recorded",
  "status": "done",
  ...
  "request_params": {
    "audio_url": "http://files.gladia.io/example/audio-transcription/split_infinity.wav",
    "translation": true,
    "translation_config": {
      "model": "base",
      "target_languages": [
        "fr",
        "es"
      ]
    }
  },
  "result": {
    "metadata": {
      "audio_duration": 20.555465,
      "number_of_distinct_channels": 1,
      "billing_time": 20.555465,
      "transcription_time": 21.047
    },
    "transcription": {
      "full_transcript": "Split infinity in a time when less is more where too much is never enough there is always hope for the future the future can be read from the past the past foreshadows the present and the present hasn't been written yet"
    },
    ...
  }
  ...
}

Ta-da 🎉 you just made your first transcription!

🎮 Using our playground

Using Gladia’s playground is a convenient way to test our speech to text API. On the playground you are able to transcribe remote audio files through URL, and also upload your local audio files, alongside with live audio transcription.

Select your audio source

Choose your audio source (using an audio link, or upload a local file)

Then proceed to the next step.

Select features

You’ll be able to select Gladia API provide for your transcription. For this example, we want to detect the speakers, so we turned on diarization.

Only a few features of Gladia API are available on the playground. For more advanced testing, check our API documentation instead.

Transcribe

You can see an already formatted and readable results in the default “Transcription” tab, and you’ll also find the result in various format (plain text, SRT, VTT) and JSON (the one you’d get with an API call).

🥳 Congratulation, you just transcribed your first audio file with Gladia.

Gladia API offers way more than state of the art speech-to-text. Take a look here to take your audio transcriptions to the next level.

Introduction

Getting started

Speech to Text API

Audio Intelligence

Limits & Specifications

Transcribe an audio file

🤖 Using your terminal with cURL command

🎮 Using our playground

Introduction

Getting started

Speech to Text API

Audio Intelligence

Limits & Specifications

​🤖 Using your terminal with cURL command

​🎮 Using our playground

🤖 Using your terminal with cURL command

🎮 Using our playground