Skip to main content

Dictation

Run in Postman

In this article you will learn how to convert an audio stream coming live from a microphone to text using our APIs.

Prerequisites

Make sure to follow Getting Started to log in and install the NeuralSpace Service. If you are using APIs, save your authorization token in a variable called AUTHORIZATION_TOKEN before moving ahead.

Dictation

Using the CLI

To transcribe audio using the CLI, use the following commands.

To get the list of supported languages, run the command mentioned below.

Get supported languages
neuralspace transcription get-languages

To get your microphone's device ID, run the command mentioned below. The device number with a * mark or a > mark would be your default microphone's device ID.

Get device ID
neuralspace transcription list-devices

Finally, to start transcribing, run the following command. Pass audio language in -L, domain in -dom and device ID in -d.

Get transcriptions
neuralspace transcription stream -L "en" -dom "general" -d 23
AttributeRequiredTypeDescription
--language or -LTruestrSet to the language of the audio that you want to transcribe.
--domain or -domFalsestrSet to the required domain of the audio. If no value is provided, then General is automatically selected.
--device or -dTrueintSet to the microphone device ID that you want to use.

The output would look something like this:

Output
Transcription ::  {"text": "", "full": 0}
Transcription :: {"text": "hello world", "full": 0}
Transcription :: {"text": "hello world", "full": 1}
Results
  • When the sentence is still being transcribed, the full attribute in the output would be 0.
  • When the sentence is completed, it will change to 1 and some grammar might be fixed in the final sentence.
  • The sentence is considered to be completed when there is a small pause after the sentence.

Using the UI

You can also use our Platform UI to easily convert your speech to text, live as you speak.
Have you tried it out yet? Head over to our step by step guide on quickly setting up and using the UI to transcribe your files! 🙌

What's Next?

  • Check out the language support page for transcribing in differnet languages or for different domains.