gemini Gemini Python SDK Releases · · 2.19.0

Python GenAI Client Library Adds Audio Transcription Modes and Configuration Options

sdkaideprecationengineer
feature

The `googleapis/python-genai` library version 2.19.0 introduces new `mode` enums (`VERBATIM`, `SMART`) for `AudioTranscriptionConfig` and `TranscriptionConfig` to enhance control over audio processing. This release also adds parameters for video resolution and extension tasks, as well as `enable_data_retention` to `ToolParallelAiSearch` and `step_count` to `ReinforcementTuningHyperParameters`. Additionally, an `IDLE` state has been added to the live connection status enum, and `REQUIRES_ACTION` is now marked as deprecated. These updates expand the capabilities for developers working with Google's generative AI services.

  • Add mode enum (VERBATIM, SMART) to AudioTranscriptionConfig and TranscriptionConfig
  • Add enable_data_retention to ToolParallelAiSearch, Add step_count to ReinforcementTuningHyperParameters, Add BidiGenerateContentSetup
  • Add IDLE state to live connection status enum and mark REQUIRES_ACTION as deprecated
  • Add video resolution and extension task parameters
Features (4)
  • Add mode enum (VERBATIM, SMART) to AudioTranscriptionConfig and TranscriptionConfig
  • Add enable_data_retention to ToolParallelAiSearch, Add step_count to ReinforcementTuningHyperParameters, Add BidiGenerateContentSetup
  • Add IDLE state to live connection status enum and mark REQUIRES_ACTION as deprecated
  • Add video resolution and extension task parameters
Read the original announcement →

https://github.com/googleapis/python-genai/releases/tag/v2.19.0

Related releases