Synthesizes natural-sounding speech by applying powerful neural network models.

Required Ruby Version

>= 3.2

Authors

Google LLC

Versions

  1. 2.3.0

    1. source

      1. 2.3.0 source November 05, 2026 (14 KB)
  2. 2.2.1

    1. source

      1. 2.2.1 source October 01, 2026 (14.5 KB)
  3. 2.2.0

    1. source

      1. 2.2.0 source June 11, 2026 (14.5 KB)
  4. 2.1.0

    1. source

      1. 2.1.0 source March 20, 2026 (14.5 KB)
  5. 2.0.3

    1. source

      1. 2.0.3 source September 12, 2025 (14.5 KB)
Show all versions (39 total)

Pushed by

google-cloud

SHA 256 checksum

← Previous version