timetobail

Azure OpenAI in Foundry Models · Forced move · Tracked since October 17, 2026 · Sources checked Oct 17

Time to bail on Azure OpenAI tts, tts-hd and whisper deployments?

Time to Bail · Boarding pass

FromAzure OpenAI tts, tts-hd and whisper deployments
ToYour pick

Act. You can stay.

These audio models end December 15, 2026. Microsoft has not named a model to use next.[1]

Act means: change a setting or plan before the date. You can stay.

Gate closes
Retirement date
Time left
58days
Status
Act

Azure OpenAI tts, tts-hd and whisper retire December 15, 2026

Microsoft retires the tts, tts-hd and whisper models, version 001, in Azure OpenAI on December 15, 2026. Its list does not name a model to use next.

Email me 7 days before Dec 15

One email with the first steps. Nothing else.

Or add the date to your calendar: Apple or Outlook (.ics) · Google Calendar

What to do before December 15

Tick steps as you go. Your progress stays in this browser.

  1. List your audio deployments

    Check each Azure OpenAI deployment of tts, tts-hd and whisper.

  2. Pick a newer audio model

    gpt-4o-mini-tts and gpt-4o-mini-transcribe version 2025-12-15 run to June 15, 2027.

  3. Test before December 15

    Try real audio. Check quality, speed and cost, then switch your app.

Email me 7 days before Dec 15

One email with the first steps. Nothing else.

Or add the date to your calendar: Apple or Outlook (.ics) · Google Calendar

Facts we checked

Facts and their sources
Retirement dateDecember 15, 2026[1]
Models and versionstts 001 (Preview), tts-hd 001 (GA), whisper 001 (GA)[1]
ReplacementNone listed yet[1]
Audio models with later datesgpt-4o-mini-tts and gpt-4o-mini-transcribe version 2025-12-15: June 15, 2027[1]
On the OpenAI API itselftts-1 and tts-1-hd end January 6, 2027; whisper-1 ends February 26, 2027[3]
After retirementAll inference requests return 410 Gone[2]
Can you get more time?No. Microsoft says retirement dates are not extendable[2]
Deployments of these modelsStop answering on December 15, 2026[1]

After December 15, 2026 you will see

Requests to retired deployments of tts, tts-hd and whisper fail. Microsoft says inference returns an error.

410 Gone

Fix

  1. Deploy a newer audio model and point your app to it.
  2. Check dates with the Models API: read lifecycleStatus and deprecation.inference.

Source: [1] Model retirement schedule (Microsoft) · [2] Microsoft Foundry Models lifecycle and support policy (Microsoft)

Sources

Check it yourself. Every fact above links here.

  1. Model retirement schedule Microsoft · primary · checked Oct 17
  2. Microsoft Foundry Models lifecycle and support policy Microsoft · primary · checked Oct 17
  3. OpenAI API deprecations OpenAI · primary · checked Oct 17
Read the published editorial report

What changed

Time to bail on Azure OpenAI tts, tts-hd and whisper deployments? Act. You can stay. These audio models end December 15, 2026. Microsoft has not named a model to use next.

On our scale this is Act: change a setting or plan before the date. You can stay.

Microsoft retires the tts, tts-hd and whisper models, version 001, in Azure OpenAI on December 15, 2026. Its list does not name a model to use next.

Here are the facts we checked:

  • Retirement date: December 15, 2026 (Microsoft)
  • Models and versions: tts 001 (Preview), tts-hd 001 (GA), whisper 001 (GA) (Microsoft)
  • Replacement: None listed yet (Microsoft)
  • Audio models with later dates: gpt-4o-mini-tts and gpt-4o-mini-transcribe version 2025-12-15: June 15, 2027 (Microsoft)
  • On the OpenAI API itself: tts-1 and tts-1-hd end January 6, 2027; whisper-1 ends February 26, 2027 (OpenAI)
  • After retirement: All inference requests return 410 Gone (Microsoft)
  • Can you get more time?: No. Microsoft says retirement dates are not extendable (Microsoft)
  • Deployments of these models: Stop answering on December 15, 2026 (Microsoft)

You can stay on Azure OpenAI in Foundry Models. You have to change a setting or plan before the date.

Leaving is a choice here, not a must.

Microsoft is the main source for this page. Azure OpenAI in Foundry Models has not said more than what is listed here. If a fact is not on this page, we do not know it yet.

Who is affected

Deployments of these models: Stop answering on December 15, 2026.

The date to remember is December 15, 2026. Make the change before then.

What to do before December 15

  1. List your audio deployments. Check each Azure OpenAI deployment of tts, tts-hd and whisper.
  2. Pick a newer audio model. gpt-4o-mini-tts and gpt-4o-mini-transcribe version 2025-12-15 run to June 15, 2027.
  3. Test before December 15. Try real audio. Check quality, speed and cost, then switch your app.

A few tips:

  • Make the change yourself before the date. Do not wait for the last reminder email.
  • Write down your current plan or settings first, so you can compare after the change.
  • After the change, open your settings again and check that it worked.

How to tell your users

If the change affects your members or team, send one short email. Say what changes for them and when. Put the most important line first.

If there is a date, send a short reminder a few days before it. Keep a copy of the list you sent it to.

Options people mention

Listed for convenience. Not ranked. Not paid. These names come up in threads and reviews; that does not show where people moved.

Before you pay, check the price page of each tool yourself. Prices change, and we only list what our sources say.

Questions people ask

No questions collected yet.

Sources

Thanks.

Did this answer your question?

Run SaaS spend at work? Get these changes before the invoice

Arrivals · for builders

Building where they land?

People on Azure OpenAI tts, tts-hd and whisper deployments can stay if they make the change. Some would rather leave. Get the playbook for this change, and list your product here.

Listing is free. An editor checks it. Not ranked. Not paid.