Python Generative AI SDK 2.9.0-rc1: New Models and Audio Features
sdkaipreviewmedia
feature
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
Features (5) ›
- 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
Read the original announcement →
https://github.com/googleapis/python-genai/releases/tag/v2.9.0-rc1
Related releases
- Google showcases 7 ways Gemini enhances student productivity in Workspace Gemini Blog ·
- Gemini Live adds new voice-activated productivity features with Spark integration Gemini Blog ·
- Google introduces Gemini 3.5 Transcribe for precise, intelligent speech-to-text Gemini Blog ·
- Google's Python GenAI SDK v2.20.0 adds audio transcription mode and JPEG2000 support Gemini Python SDK Releases ·
- Genkit CLI Developer UI enhanced with improved logging and error visibility Genkit Releases ·
- Gemini for macOS: How to Use Intelligent Dictation Gemini Blog ·