Changelog

Version 2.2.0 - 2023-11-21

  • Adds Audio Quality datapoints to all Speech services, including Signal-to-Noise ratio estimation

Version 2.1.2 - 2023-11-06

  • Security updates

Version 2.1.0 - 2023-09-20

  • Improves quality of Fluency responses by using a more accurate alignment algorithm

Version 2.0.0 - 2023-08-25

  • Reduces API response time by improving request authentication performance

Version 1.6.1 - 2023-04-24

  • Improves handling of requests that contain invalid/malformed multipart form data

Version 1.6.0 - 2023-03-28

  • Improves audio decoding performance, particularly for long, low-quality audio recordings

Version 1.5.0 - 2023-02-15

  • Increases maximum total request size to 20Mb for all Speech services

Version 1.4.0 - 2023-01-10

  • Increases maximum supported audio file duration to 2 minutes for Asynchronous requests to Speech endpoints

Version 1.2.0 - 2022-11-28

  • Retires less-efficient audio decoding method

Version 1.1.0 - 2022-11-07

  • Adds pitch/prosody datapoints to Fluency & Recognition services

Version 1.0.0 - 2022-09-28

  • Adds file object support for reference text, model id, category and user token

  • Improved response time and operational capacity

  • Production rollout of next generation of Soapbox’s API solution

Version 0.11.0 - 2022-09-09

  • Adds ‘last word heard' and 'self-correction’ features to Fluency endpoint responses

Version 0.10.10 - 2022-07-19

  • Fixes invalid/missing WAV filename headers when encountered in customer requests

Version 0.10.9 - 2022-07-04

  • Adds support for base64-encoded data files for all Speech services

Version 0.10.7 - 2022-06-09

  • Adds support for multiple reference-text targets in Verification service

Search