Dialogflow CX and Vertex AI: The text-bison-002 model will be deprecated and automatically upgraded to the gemini-1.5-flash-001 model

## Deprecate **Dialogflow CX and Vertex AI**: The `text-bison-002` model will be deprecated on **September 30, 2024** and automatically upgraded to the `gemini-1.5-flash-001` model. This change applies to **Vertex AI agents** and the following **[Dialogflow CX Generative Features](https://cloud.google.com/dialogflow/cx/docs/concept/generative)**: * Vertex AI agent apps * Data store agents (also known as Chat agents) * Generators After the upgrade on September 30, 2024, `gemini-1.5-flash-001` will be automatically selected in the console if you had previously explicitly selected `text-bison-002`. We recommend that you upgrade to the new model early to allow enough time for testing and to ensure that your solution works as intended. ## Feature **Dialogflow CX & ES**: Text-to-speech [Journey Voices](https://cloud.google.com/text-to-speech/docs/voice-types#journey%5Fvoices) now supports MULAW output `audio_encoding` ([CX](https://cloud.google.com/dialogflow/cx/docs/reference/rpc/google.cloud.dialogflow.cx.v3#outputaudioconfig), [ES](https://cloud.google.com/dialogflow/es/docs/reference/rpc/google.cloud.dialogflow.v2#outputaudioconfig)) in addition to LINEAR16\. Future updates to Journey Voices will appear in the [Cloud Text-to-Speech documentation](https://cloud.google.com/text-to-speech/docs/voice-types#journey%5Fvoices%5Fpreview). ## Change **Dialogflow CX**: Cloud Text-to-Speech `europe-west1` and `europe-west3` regions for Neural2 voices will temporarily use the `eu` mulit-region instead.