Google Generative AI Python SDK v2.14.0 adds audio transcription config
The latest release of the Google Generative AI Python SDK, version 2.14.0, introduces new configurations for audio transcription within the GenerateContent API. This update includes deprecation warnings for certain Imagen and LiveConnect configurations, signaling their upcoming removal in a future major version. The changes primarily affect developers using the SDK for generative AI tasks, particularly those involving audio or migrating from older configurations. Audio transcription configuration is now available, while older methods will be phased out.
- →[GenerateContentConfig] Add GenerationConfig.audio_transcription_config and Part.audio_transcription
- →Regenerate docs for 2.13.0
Features (1) ›
- [GenerateContentConfig] Add GenerationConfig.audio_transcription_config and Part.audio_transcription
Fixes (1) ›
Add deprecation warnings to Imagen generate_images, edit_images, generate_videos (if using prompt/text/image args), LiveConnectConfig.GenerationConfig which will be removed in the next major version
Maintenance (1) ›
- Regenerate docs for 2.13.0
https://github.com/googleapis/python-genai/releases/tag/v2.14.0
Related releases
- Google Python GenAI Library v2.23.0 Adds Environment Copying and Dynamic Turn Completion Gemini Python SDK Releases ·
- Gemini Desktop App Now Available for Windows Users Gemini Blog ·
- 4 ways Gemini makes administrative chores quick and easy Gemini Blog ·
- Lyria 3.5 music generation model generally available in Gemini Gemini Blog ·
- Genkit Python SDK v0.11.0 Improves Error Handling, Video Integration, and Model Configuration Genkit Releases ·
- Genkit Go v1.13.1 Retracts v1.13.0 and Corrects A2UI Plugin Path Genkit Releases ·