Vovsoft Logo
Vovsoft Facebook Page Vovsoft Twitter Account
Menu
Home » Blog Posts » How to Use Speech to Text Converter

How to Use Speech to Text Converter

Date Last updated 5 months ago
*****
Rate this blog post

API Settings

"Vovsoft Speech to Text Converter" supports IBM Cloud Speech to Text API which can convert up to 500 minutes per month for free.

In order to obtain your API key and URL, please follow these steps:

  1. Go to https://cloud.ibm.com/registration and create your IBM Watson Cloud account for free.
  2. Go to https://cloud.ibm.com/catalog/services/speech-to-text and create your Speech to Text Lite Plan instance.
  3. Go to https://cloud.ibm.com/resources; under Services tab, click on your Speech to Text instance. Your credentials (API key and URL) will be displayed in Manage or Service credentials page.

IBM Cloud Credentials

Enter your API key and URL into the Settings panel inside "Vovsoft Speech to Text Converter". The software is now ready to convert audio to text.

Broadband models vs Narrowband models

For most languages, the IBM Cloud service supports both broadband and narrowband models:

  • Broadband models are for audio that is sampled at greater than or equal to 16 kHz.
  • Narrowband models are for audio that is sampled at 8 kHz. Use narrowband models for offline decoding of telephone speech, which is the typical use for this sampling rate.

Choosing the correct model is important. Use the model that matches the sampling rate (and language) of your audio. The service automatically adjusts the sampling rate of your audio to match the model that you specify.

Common Errors

HTTP/1.1 503 Service Unavailable

Your URL is wrong. Please enter the exact "API Key" and "URL" that was supplied for you by IBM Cloud.

Error reading data: (12152)

Your audio is too long. Please try to convert a shorter audio.

Speech to Text Converter Icon Speech to Text Converter Windows


Continue Reading


Comments Responses (1)


Avatar Image
Alexandre
Apr 6, 2021 at 09:33 pm (GMT) | Reply
Creating an account took a bit of a challenge, but it's the best speech2text I've ever tried.

Leave a Comment