Chirp 2

Speech recognition and translation built on the Universal Speech Model: audio in, transcription or translation text out. Streaming and batch modes.

Модель прошлого поколения, вендор до сих пор даёт выбрать её в Cloud Speech-to-Text API V2. Месяц выхода на страницах вендора не указан.

Understands

audio

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.