Skip to content

v2.5.0

Choose a tag to compare

View all tags
@rotemdan rotemdan released this 31 Mar 09:37
· 87 commits to main since this release
v2.5.0
25eae87

Enhancements

  • OpenAI cloud TTS: add support for the new gpt-4o-mini-tts model. Update voice list and list of supported languages
  • OpenAI cloud STT: add support for the new gpt-4o-mini-transcribe and gpt-4o-transcribe models
  • CLI isolate: use higher bitrates for lossy compressed output audio (mp3, opus, mp4 and ogg). 64kbps for isolated speech and 128kbps for background audio, instead of the defaults (defaults range between 48kbps to 64kbps - optimized for mono speech)
  • Add 2 corrections to the English pronunciation lexicon

Full Changelog: v2.4.0...v2.5.0

Assets 2
Loading