Quickstart

This Quickstart guide is intended for developers who are familiar with sending HTTP requests to RESTful Web Services and using tools such as CURL.

The following steps send HTTP Requests to the various SoapBox Labs RESTful Web Services. This is intended for test purposes only. For Production deployments, please consult the full Developer Docs, in particular Authentication. Each endpoint requires an App Key. Your app key is available within the Account page of the SoapBox Labs Portal or can be requested through our Support Desk.

These examples all interact with the SoapBox Labs Web Services in a synchronous manner. Asynchronous processing of requests is also available and is priced differently (please contact us for pricing information). More information is available here.

Fluency Quickstart

Our Fluency solution is built on top of our STT solution and provides an extra layer of analysis of the submitted audio file. Please refer to the following article for further details on SoapBox Labs Fluency solution.

As with all requests to the SoapBox Labs Web Service solutions, the Fluency endpoint requires the presence of a user_token parameter. This can be any alphanumerical value that the customer should specify and should uniquely identify the speaker in the attached audio sample. More information on the user_token field is available here.

The Fluency API is an synchronous Speech service with an endpoint located at...

https://api.soapboxlabs.com/v1/speech/fluency

For quick tests you can use a tool called CURL (Mac & Linux) and the following sample CURL command...

curl -H “x-app-key:APP_KEY_HERE“ /
      -F "file=@AudioFile.wav" /
      -F "reference_text=@ReferenceText.txt"
      -F "model_id=MODEL_ID" /
      -F "user_token=USER_TOKEN_HERE" /
      https://api.soapboxlabs.com/v1/speech/fluency

For an explanation of the JSON response structure please refer to the Fluency documentation here.

Speech-To-Text (STT) Quickstart

Please refer to the following article for further details on SoapBox Labs Speech-To-Text solution.

As with all requests to the SoapBox Labs Web Service solutions, the Speech-To-Text endpoint requires the presence of a user_token parameter. This can be any alphanumerical value that the customer should specify and should uniquely identify the speaker in the attached audio sample. More information on the user_token field is available here.

The Speech-To-Text API is synchronous Speech service with an endpoint located at...

https://api.soapboxlabs.com/v1/speech/recognition

For quick tests you can use a tool called CURL (Mac & Linux) and the following sample CURL command...

curl -H “x-app-key:APP_KEY_HERE“ /
      -F " file=@AudioFile.wav" /
      -F "model_id=CLM_ID" /
      -F "user_token=USER_TOKEN_HERE" /
      https://api.soapboxlabs.com/v1/speech/recognition

For an explanation of the JSON response structure please refer to the following article.

Speech Verification Quickstart

Please refer to the following article for further details on SoapBox Labs Verification solution.

As with all requests to the SoapBox Labs Web Service solutions, the Verification endpoint requires the presence of a user_token parameter. This can be any alphanumerical value that the customer should specify and should uniquely identify the speaker in the attached audio sample. More information on the user_token field is available here.

The synchronous Verification API endpoint is located at...

https://api.soapboxlabs.com/v1/speech/verification


For quick tests you can use a tool called CURL (Mac & Linux) and the following sample CURL command...

curl -H “x-app-key:APP_KEY_HERE“ /
      -F " file=@AudioFile.wav" /
      -F "user_token=USER_TOKEN_HERE" /
      -F "category=orange" /
      https://api.soapboxlabs.com/v1/speech/verification


In the above request, an audio file is submitted to the Verification API with a target of “orange“. Verification calls require one or more target prompts to search for within the audio file. The speech contained in the audio file will be scored against these targets and a JSON response detailing the analysis will be returned. For an explanation of the JSON response please refer to the following article.

Resources

Attached is a sample audio file that you can use to test the API using the CURL commands above.

test.wav

At the moment we accept uncompressed (wav) audio samples with a minimum sampling rate of 16khz.
Please refer to the following articles for further detail on interacting with our Speech APIs.

Learn about Audio Encoding constraints of the SoapBox Labs API.

Find out out Best Practices when using the SoapBox Labs API.

Search