AndrewMultilingualNeural en-US says the wrong word when only one word to speech

TL;DR

The problem occurs when you use AndrewMultilingualNeural, en-US, and only one word. It was fixed with an updated voice model, first in eastus, with other regions following (no December deployments, ready mid January).

Steps

1. for example: The word 'abandon', the voice like you cut off the letter a. He just said 'bandon'. The problem occurs when you use AndrewMultilingualNeural, en-US, and only one word.
2. [LinZhang-Support (commenter)]: This was a backend bug on Microsoft's side, not your code: single-word synthesis with AndrewMultilingualNeural (en-US) clipped the first letter. It was fixed with an updated voice model, first in eastus, with other regions following (no December deployments, ready mid January). If you still hear it, check which region your Speech resource is deployed in.

When to use

You are seeing this: for example: The word 'abandon', the voice like you cut off the letter a. Use this skill when you run into "AndrewMultilingualNeural en-US says the wrong word when only one word to speech".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

In gh:Azure-Samples/cognitive-services-speech-sdk#2300 (https://github.com/Azure-Samples/cognitive-services-speech-sdk/issues/2300), the reporter ran into this: for example: The word 'abandon', the voice like you cut off the letter a. He just said 'bandon'. The problem occurs when you use AndrewMultilingualNeural, en-US, and only one word. The verified resolution: [LinZhang-Support (commenter)]: This was a backend bug on Microsoft's side, not your code: single-word synthesis with AndrewMultilingualNeural (en-US) clipped the first letter. It was fixed with an updated voice model, first in eastus, with other regions following (no December deployments, ready mid January). If you still hear it, check which region your Speech resource is deployed in.