> For the complete documentation index, see [llms.txt](https://docs.bottalk.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bottalk.io/docs/features/dictionaries/ssml-tags.md).

# SSML-Tags

The TTS providers Microsoft Azure Speech, Amazon Polly, and Google Wavenet support Speech Synthesis Markup Language (SSML) tags. 

SSML allows you to specify how speech is pronounced, enabling you to fine-tune text-to-speech output. You can use SSML in your custom dictionary with phonemes to improve pronunciation, as well as define how specific words, mathematical expressions, or words in different languages are pronounced.

For Microsoft the most important SSML-Tags are: 

* Phonemes: < phoneme alphabet="ipa" ph=" *insert phoneme* "> *insert original word* < /phoneme >
* English pronunciation: < lang xml:lang="en-US"> insert *orginal word* < /lang >

<figure><img src="/files/YK2tjfq45KJ0zVrq8TQm" alt=""><figcaption><p>Microsoft Azure English pronunciation</p></figcaption></figure>

<figure><img src="/files/AgxPSLnlAOiBe7f8ENec" alt=""><figcaption><p>Microsoft Azure phoneme pronunciation</p></figcaption></figure>

Further information you can read by your selected TTS Provider:&#x20;

[Microsoft Azur Speech](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-pronunciation)

[Amazon Polly](https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html)

[Google Wavenet ](https://cloud.google.com/text-to-speech/docs/ssml?hl=de)