December 2025

Speech to Text (STT)

Model APIs

Added input_audio_codec: Introduced the input_audio_codec parameter, letting you explicitly declare the audio codec when automatic detection isn’t sufficient (for example, raw PCM streams).

Translate & Transliterate

Model APIs

Deprecated enable_preprocessing: Deprecated the enable_preprocessing parameter on the Translate and Transliterate APIs. Preprocessing behavior is now handled internally, so the parameter no longer needs to be set.

SDKs

Model APIs

TypeScript SDK: Released an updated TypeScript SDK version with improved generator settings and type coverage.