unstale

npm / @ai-sdk/azure

@ai-sdk/azure

What changed in @ai-sdk/azure 3 to 4, from its official release notes, upgrade guides and advisories. Sources checked 2026-10-17.

3 breaking2 deprecations16 new APIs and options2 behavior and defaults3 fixes and other

See which of these apply to your code, ranked, in your agent:

npx @unstale/cli init

@unstale/cli 0.1.0 on npm

@ai-sdk/azure 421 changes

Breaking changes 3

  • Azure Speech voice-reset errors from unknown voices or unsupported styles now report status 400 instead of 502, preventing retries for client input errors.

    3.0.134, 4.0.91release notesrelease notes

  • Unknown MAI voices or styles now produce descriptive, non-retryable errors.

    3.0.133, 4.0.90release notesrelease notes

  • Rejects resourceName values that are not single DNS labels, preventing malformed values from rewriting the request host.

    3.0.131, 4.0.84release notesrelease notes

Deprecations 2

  • Deprecated in favor of azure.tools.webSearch().

    4.0.104release notes

  • Deprecated or ineffective DeepSeek sampling options now produce warnings and are omitted, while penalty sampling remains supported for Azure-hosted DeepSeek models.

    3.0.107, 4.0.49release notesrelease notes

New APIs and options 12

  • Adds support for MAI-Image models through the MAI image API.

    3.0.135, 4.0.92release notesrelease notes

  • Adds streaming transcription support through the MAI realtime API.

    4.0.90release notes

  • Adds speech generation support for MAI-Voice-2.1 through the MAI realtime API.

    4.0.90release notes

  • Adds speech generation support for MAI-Voice-2.1-Flash through the MAI realtime API.

    4.0.90release notes

  • Adds the maiBaseURL setting for MAI realtime API integration.

    4.0.90release notes

  • Adds providerOptions.azure.api: 'mai' to select the MAI realtime API.

    4.0.90release notes

  • Adds the webSocket setting for MAI realtime API integration.

    4.0.90release notes

  • Adds MAI-Transcribe-2 file transcription through the Azure Speech API with diarization, timestamps, transcript styles, locale forcing, and phrase lists.

    3.0.128, 4.0.83release notesrelease notes

  • Adds azure.transcriptionModel as an alias of azure.transcription.

    3.0.128, 4.0.83release notesrelease notes

  • Adds an Azure API provider option that overrides model-based routing for speech generation.

    3.0.131, 4.0.83release notesrelease notes

  • Adds a setting for configuring the Azure Speech endpoint.

    3.0.128, 4.0.83release notesrelease notes

  • Exports OpenAIResponsesSystemMessageOptions for typed message-level reasoning effort updates in Azure Responses models.

    2.0.137, 3.0.126, 4.0.79release notesrelease notesrelease notes

Behavior and default changes 1

Fixes and other changes 3

  • Hostname parts are now validated using isValidHostnamePart, affecting hostname validation for configured Azure endpoints.

    4.0.87release notes

  • Uses a standards-compliant User-Agent header.

    4.0.84release notes

  • Constructs OpenAI v1 URLs for Azure AI Foundry and Cognitive Services hostnames while preserving complete v1 and Foundry project base URLs.

    2.0.129, 3.0.113, 4.0.55release notesrelease notesrelease notes

@ai-sdk/azure 35 changes

New APIs and options 4

  • Adds support for MAI-Voice-2.1 and MAI-Voice-2.1-Flash speech generation.

    3.0.133release notes

  • Adds MAI-Voice-2-Flash and MAI-Voice-2 speech generation through Azure Speech text to speech with voice, output format, speed, and style options.

    3.0.131release notes

  • Adds azure.speechModel() as an alias of azure.speech().

    3.0.131release notes

  • Adds an Azure provider option to override model-based API routing for transcription.

    3.0.128release notes

Behavior and default changes 1

  • Requests route to the Azure Speech API by default and no longer send rejected segment timestamp defaults.

    3.0.131release notes