Skip to main content

Download Speech Platform

Step #1 – Download​

Try and evaluate all Phonexia speech technologies either via REST API using Speech Engine, or using the demo/testing GUI application named Phonexia Browser.

Hardware Requirements
  • Recommended: Intel Core i7 or better, 32 GB free RAM, 10+ GB storage (SSD preferred)
  • Minimum: Intel Core i5, 16 GB free RAM, 10 GB storage (SSD preferred) :::
warning

To prevent various issues and malfunctions, please take the free RAM requirement seriously. See also additional information on Recommended OS and HW page.

While downloading, you can check the updates: Speech Engine changes and Browser changes.

This package allows new users to try and evaluate Phonexia Speech Platform.

Phonexia Speech Platform 3.63.0 for Windows 64-bit
4 GB
Phonexia Speech Platform 3.63.0 Linux 64-bit
4 GB

To keep the download size reasonable, the package includes only English models for Speech to Text and Keyword Spotting. Additional supported languages are available upon request.

Speech Engine – technologies included
  • Speech Engine – technologies included:
    • Speech to Text (STT) – model EN_US_6 (US English)
    • Keyword Spotting (KWS) – model EN_US_6 (US English)
    • Phoneme Recognizer (PHNREC) – model EN_US_6 (US English)
    • Speaker Identification 4 (SID4) – model XL5
    • Diarization (DIAR) – model XL4
    • Language Identification (LID) – model L4
    • Gender Identification (GID) – model XL5
    • Age Estimation (AGE) – model XL5
    • Voice Activity Detection (VAD) – model GENERIC_3 and SID4_XL5
    • Speech Quality Estimation (SQE)
    • Time Analysis Extraction (TAE)
    • Waveform Denoiser (DENOISER)

  • Phonexia Browser
  • example audio
    • (in ./BROWSER/example/ and ./SPE/bsapi/{technology}/example/)

Step #2 – First start​

To get started, please follow one of the two methods:

Further information and resources​

  • Speech Engine REST API documentation

  • Tutorials and training videos: see technologies introduction video