Speech-to-Text release notes

Facts taken from this source

• Google Cloud updated the generally available Chirp 2 model on October 7, 2024, to improve its accuracy and multilingual capabilities.

  “October 07, 2024 Feature Speech-to-Text has updated the Generally Available Chirp 2 model, further enhancing its ASR accuracy and multilingual capabilities.” (Release notes entry dated October 07, 2024)

• Google Cloud launched a new Speech-to-Text model named chirp_telephony on January 8, 2024, for telephony audio.

  “January 08, 2024 Feature Speech-to-Text has launched a new model, named chirp_telephony” (Release notes entry dated January 08, 2024)

• Google Cloud made the Chirp 2 model generally available on January 27, 2025.

  “January 27, 2025 Feature Speech-to-Text is generally available (GA) in the Chirp 2 model” (Release notes entry dated January 27, 2025)

• Google Cloud announced the general availability of Chirp 3: Transcription on October 13, 2025, as the latest generation of its multilingual ASR model.

  “October 13, 2025 Feature Speech-to-Text is excited to announce the General Availability (GA) of the Chirp 3: Transcription, the latest generation of Google's multilingual Automatic Speech Recognition (ASR)-specific generative model” (Release notes entry dated October 13, 2025)

• Google Cloud launched chirp_3 in private preview on April 11, 2025.

  “April 11, 2025 Feature Speech-to-Text has launched chirp_3 in Private Preview.” (Release notes entry dated April 11, 2025)

• Google Cloud launched chirp_3 in public preview on August 29, 2025.

  “August 29, 2025 Feature Speech-to-Text has just launched chirp_3 in Public Preview.” (Release notes entry dated August 29, 2025)