This page will walk you through how to use WSL's Respellings system to shape a word's pronunciation.

WSL's respellings system allows you to give precise pronunciation instructions to the AI.

Respellings let you format a word within the text body param in a manner that tells the AI exactly what sound each syllable should make—and which syllables should be emphasized.

You can query the WellSaid respelling_suggestion database using the respelling_suggestions API call.

A respelling is composed of the following components:

  • each individual syllable, spelled using consonants and vowels representing specific sounds (please reference the Respellings Chart for those mappings)
  • a dash separating each individual syllable
  • at least one capitalized syllable to indicate word stress
  • unstressed syllables remain in lowercase

Using Respellings

Every respelling must be contained within two colons.

For example, "tuple" is respelled as ::TUH-puhl::. The noun form of "live" is respelled as ::LYV::.

To make a call using a respelling, simply include the formatted respelling in your raw data input in the text body parameter:

curl --location --request POST 'https://api.wellsaidlabs.com/v1/tts/stream' \
--header 'X-Api-Key: YOUR_API_KEY' \
--header 'Accept: audio/mpeg' \
--header 'Content-Type: application/json' \
--data-raw '{
  "text": "Coming in ::LYV:: from Seattle!",
  "speaker_id": "3"
}' > live.mp3

BETA TTS Model

📘

NOTE: If you are using our BETA TTS Model, then you will use the following markup to pass in a replacement instead of the two colons listed above.

When sending a respelling to our BETA TTS Model you need to pass through two variables, the original text and the replacement value. So in the example where we want to replace "live" with "LYV" we would wrap it like so:

"Coming in <respell value="LYV">live</respell> from Seattle!"

curl --location --request POST 'https://api.wellsaidlabs.com/v1/tts/stream' \
--header 'X-Api-Key: YOUR_API_KEY' \
--header 'Accept: audio/mpeg' \
--header 'Content-Type: application/json' \
--data-raw '{
  "text": "Coming in <respell value="LYV">live</respell> from Seattle!",
  "speaker_id": "3"
}' > live.mp3

Respellings Reference Chart

Vowels Consonants
To hear as in type For example, To hear as in type For example,
a ant A ::ANT:: b bunk B ::BUHNK::
a spa AH ::SPAH:: ch chart CH ::CHAHRT::
a all AW ::AWL:: d dust D ::DUHST::
a eight AY ::AYT:: f first F ::FURST::
e egg EH ::EHG:: g glow G ::GLOH::
e ease EE ::EEZ:: h horse H ::HORS::
i in IH ::IHN:: j jell J ::JEHL::
i isle Y ::YL:: k kite K ::KYT::
o oat OH ::OHT:: l laugh K ::LAF::
o ooh OO ::OO:: m mask M ::MASK::
o foot UU ::FUUT:: n nest N ::NEHST::
u up UH ::UHP:: ng ring NG ::RIHNG::
nk rink NK ::RIHNK::
p pop P ::PAHP::
VOWEL COMBINATIONS qu quote KW ::KWOHT::
To hear as in type For example, r rain R ::RAYN::
ar car AR ::KAR:: s slice S ::SLYS::
er error ERR ::ERR-ur:: sh shy SH ::SHY::
or more OR ::MOR:: t tarte T ::TART::
ow cow OW ::KOW:: th though DH ::DHOH::
oy oy OY ::OY:: th think TH ::THIHNK::
ur urn UR ::URN:: v van V ::VAN::
w win W ::WIHN::
x axe KS ::AKS::
y yes Y ::YEHS::
z zen Z ::ZEHN::
zh measure ZH ::MEH-zhur::