Model retirement - update to what? gpt-4o-transcribe

Hi Daniel Müller,
The message you are seeing means that the current version of gpt-4o-transcribe you are using (2025-03-20) will stop working on October 15, 2025. After that date, any calls to this version will return errors.

Right now, do not see an option to update because a newer version of gpt-4o-transcribe has not yet been released. Once Microsoft publishes the next version, you will be able to edit your deployment and move to that supported version.

For now, your service will continue working as it is. We recommend that you regularly check the Azure OpenAI What’s New page. That is where updates about new model versions and retirement dates are posted.

Hello Daniel Müller,

Welcome to the Microsoft Q&A and thank you for posting your questions here.

Regarding your explanation, my recommended replacement model should be:

Model Name: gpt-4o-mini-transcribe

Version: 2025-03-20

Advantages:

• Faster transcription
• Lower latency
• Better performance in noisy environments and accents - https://ai.azure.com/catalog/models/gpt-4o-mini-transcribe

You can update deployment (If Portal UI Fails) via REST API by using the following structure to update your deployment manually: Endpoint:

PUT https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments/{deploymentName}?api-version=2023-05-01

Request Body:

{
  "sku": {
    "name": "Standard",
    "capacity": 120
  },
  "properties": {
    "model": {
      "format": "OpenAI",
      "name": "gpt-4o-mini-transcribe",
      "version": "2025-03-20"
    },
    "versionUpgradeOption": "Manual"
  }
}

You can also check region availability:

• gpt-4o-mini-transcribe is currently available in East US2 and other selected regions - https://devblogs.microsoft.com/foundry/get-started-azure-openai-advanced-audio-models/
• If your deployment is in a region where the model is not yet available, you may need to:
  • Create a new deployment in a supported region.
  • Use Azure resource health alerts to monitor availability - https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/model-retirements

I hope this is helpful! Do not hesitate to let me know if you have any other questions or clarifications.

Please don't forget to close up the thread here by upvoting and accept it as an answer if it is helpful.