Python Generative AI SDK 2.9.0-rc1: New Models and Audio Features

The Python Generative AI SDK has released version 2.9.0-rc1, introducing support for new models like gemini-3-flash-preview and enhancing audio transcription capabilities with features such as audioOffset and LanguageAuto. These updates benefit developers working with multimodal AI applications, particularly those involving audio processing. The release also broadens publisher model path checks, improving compatibility. This is a preview release.

• →Add audioOffset to VoiceActivity
• →Add gemini-3-flash-preview (gemini-3.1, gemini-3.5, gemini-4 are already mapped) to the local tokenizer map. , closes #1972
• →Add interimInputTranscription to LiveServerContent
• →Add LanguageAuto, LanguageHints, and adaptationPhrases to AudioTranscriptionConfig
• →Broaden publisher model path check to support all publishers