Skip to main content

Version 2.0.0

· One min read
  • Added Time Analysis of Speech technology (high-level description), available via REST API only (no GUI).
  • Configuration and administration changes:
    • Added options to change tmpdir volume for speech-platform API and media-conversion.
    • Added options to configure UI limits.
    • Added option to change API log level.
    • Models are now stored on data disk separately for each microservice.
Included Components
  • Speech to Text Phonexia 6th Generation 3.60.1
  • Speech to Text Whisper Enhanced 1.1.0
  • Time Analysis of Speech 3.60.1
  • Voiceprint Comparison 1.0.0
  • Voiceprint Extraction 1.2.0

Version 1.1.0

· One min read
  • Initial release with Speaker Identification ([high-level description(/products/speech-platform-4/technologies/speaker-identification)) and Speech To Text (high-level description) technologies available via REST API and in GUI. The Speech to Text Whisper Enhanced supports auto-detection of the language.
Included Components
  • Speech to Text Phonexia 6th Generation 3.60.1
  • Speech to Text Whisper Enhanced 1.0.1
  • Voiceprint Comparison 1.0.0
  • Voiceprint Extraction 1.0.0