Scripts are never set in stone at the start of a project. They
usually are modified quite often before the project is considered
complete. One of the reasons is that when we read a script, it may
sound quite different in our heads than when we hear it spoken out
loud. This alone leads to script changes as we note phrases that
sound awkward or that are otherwise not clear. Although The speech
engines are improving, but still say some odd things. We cannot
avoid some ‘funnies’, so we should do everything possible to amend
ones that we can express more suitably. Please listen to what you
write, and remember that the voices vary in their pronunciation.
By using ingenious spellings: since speech services are based on
predictions , words might be mispronounced at times. There is no
way to preset the pronunciations for words in a voice
dictionary. If a word is being pronounced incorrectly, you must
modify the script to make it sound the way it should. For
instance,To speak heteronyms like “the war was lead by the
chief” and “lead is a metal” . both the words have same
spellings but are pronounced differently, hence in the second
sentence, give the input as led, as how you want it to be
Use manual numbers: We say millions, thousands and hundreds and
so does most TTS. However, we say, e.g. Charity Numbers and
ISBNs as single digits. TTS does not. We cannot do anything
Eg: Population 1,234,567 and Registered Charity
Number 1234567890. It might call out the number as one billion
two hundred thirty-four million five hundred sixty-seven
thousand eight hundred ninety, and we probably do not want that
so type in individual numbers or how you want the TTS to
pronounce it as. Either one two three or twelve three forty
five. Fiddle with the words at your ease and comfort.
Add pauses: For your text to sound rhythmic, natural, as living
beings, The easiest improvement is punctuation. If a human
reader would pause and let his or her voice drop, we need to
indicate this in text. Some TTS will pause at hard return line
ends, but not all. So always put stops. This can be done by
adding commas,periods,dashes and ellipses. Think of them as
percussive notes. For instance to give a long pause, you may use
three dots(…), or for a shorter pause, may use comma(,).
ASAP or A.S.A.P. This is perhaps the most controversial item in
writing for TTS. All TTS says ASAP as letter names, but it is a
good idea, as a principle, to put A.S.A.P. with stops, as a
reminder of all the recommendations in this document! for
instance, you may write the script as “I want the work done
A.S.A.P.” in place of “I want the work ASAP”.
Compound words: Put hyphens in compound words, because TTS does
not always know where to split them. For example the word
“high-tech” sounds better than when input as high tech.
Play with intonation: if you want to emphasize a certain word,
try to put it in quotation marks.“The judicious use of
punctuation goes a long way towards making the voices more
expressive and precise, especially the comma and the colon.”
How to effectively use punctuation?
Use more punctuation, to make the voice pause and drop in tone.
- Put stops after headings and sub-headings.
- Use stops or semi-colons after each bullet point.
- Put stops after numbers in lists.
- Insert commas and colons.
- Use straight quotation marks and apostrophes.
Not all TTS knows that No. means Number, Vol. means
Volume. mins means minutes. So refrain using abbreviations and
rather use full words like “I will be there in ten minutes”
rather that “ I will be there in ten mins”.