Overriding pronunciations

​

Background

It’s sometimes the case that a word is not pronounced the way you expect. This most frequently happens for proper nouns (e.g. “Weber” can be pronounced “web-er” or “wee-ber”) and homographs (e.g. “lead” can be pronounced “led” or “leed”).

​

Pronunciation tags

When this happens, you can use pronunciation tags to override the default pronunciation. These tags are inserted into your input text and tells the API how to pronounce a word.

The tag format is [word : arpabet] where word is the word you want pronounced differently and arpabet is a space-separated list of ARPABET phonetic symbols. Tags are insert in-line with your input text.

Example: The [quick: K W IH1 K] brown fox jumps over the lazy dog.

​

What is ARPABET?

ARPABET is a set of symbols that correspond to phonemes in English. It’s like a “phonetic alphabet” that’s used to indicate how a word is pronounced.

We support a simplified version of ARPABET as shown below. We also use stress markers (numbers after each vowel) to indicate which syllable is emphasized. For example, EMphasis → EH1 M F AH0 S IH0 S whereas emphaSIS → EH2 M F AH0 S IH1 S

Vowels: AA AE AH AO AW AY EH ER EY IH IY OW OY UH UW

Consonants: B CH D DH F G HH JH K L M N NG P R S SH T TH V W Y Z ZH

The mandatory number after a vowel indicates different levels of stress as follows:

e.g. AA0 AA1 AA2

Example pronunciations:

• Quack → K W AE1 K
• Spider → S P AY1 D ER0
• Mango → M AE1 NG G OW0