Using Canadian French Text to Speech

The Tellme Voice Application Network supports two female voices (isabelle and harmonie) and one male voice (claude) for Canadian French Text to Speech (TTS) processing. This article demonstrates how to access this functionality.

To access this TTS functionality, set the name attribute of the voice element to "harmonie or isabelle or claude" as shown in the following example.

<?xml version="1.0" encoding="iso-8859-1"?>
<vxml version="2.1"
  xmlns="http://www.w3.org/2001/vxml">
  <form>
    <block>
      <prompt>
        <voice name="isabelle">
          Salut Jeanne ! dit Pierre. Comment vas-tu ? 
          Ah, salut Pierre ! crie Jeanne.
          As-tu passe un bon weekend ? Oui, merci, repond-elle. Mais... 
          Attends, je dois te dire quelque chose d'important  
        </voice>
      </prompt>
      <exit/>
    </block>
  </form>
</vxml>

This functionality can also be used by setting only xml:lang. In that case the default voice will be isabelle.

<?xml version="1.0" encoding="iso-8859-1"?>
<vxml version="2.1"
  xmlns="http://www.w3.org/2001/vxml">
  <form>
    <block>
      <prompt>
        <voice xml:lang="fr-CA">
           Salut Jeanne ! dit Pierre. Comment vas-tu ? Ah, salut Pierre !
           As-tu passe un bon weekend ? Oui, merci, repond-elle. Mais... 
          Attends, je dois te dire quelque chose d'important
        </voice>
      </prompt>
      <exit/>
    </block>
  </form>
</vxml>

For information about the Speech Synthesis Markup Language (SSML) elements that the TTS engine supports, see the Speech Synthesis Markup Element Reference.

This section covers how phone numbers and mailing addresses should be formatted and how they are read by the TTS engine

  • Brief time breaks occur between number segments.
  • Phone numbers are not pronounced in pairs, as regular numbers are; digits are read individually.
    Text Pronunciation
    +33 4 74 85 21 90 "Plus trois trois quatre sept quatre huite cinq deux un neuf zero"
    33474852190 "trois trois quatre sept quatre huite cinq deux un neuf zero"
    0590 546 234 "Zero cinq neuf zero cinq quatre sixe deux trois quatre"

  • Phone number delimiters are not pronounced.
  • You can use the SSML say-as element to ensure that the TTS engine pronounces a phone number correctly.
  • Numbers in an address are read as numbers (for details, see the Numbers section)
  • United States addresses are typically in the following format:
    RECIPIENT
    [APARTMENT] [BUILDING]
    HOUSE_NUMBER [STREET_TYPE] STREET_NAME [DEPENDENT_LOCALITY]
    POSTAL_CODE LOCALITY
    FRANCE
    
  • To ensure that the TTS engine pronounces the state abbreviation correctly, be sure to include a zip code. Also, do not include extra spaces after the city name.
  • You can use the SSML say-as element to ensure that the TTS engine pronounces an address correctly.
Pronunciation Rule Text
Between a street address and a numeric street, a break occurs 57 Rue des Abbesses
A break occurs between city/state and the zip code 75018 Paris, France

Four digit numbers have some common pronunciation patterns, as listed below. You can also use the SSML say-as element to ensure that the TTS engine pronounces a number digit by digit.

Note. To express multiplication, you must write out the mathematical functions. For example, use "4 times 5" instead of "4*5" or "4X5".

Pattern Example Text Example Pronunciation
4 digit numbers without commas, decimal points 4008 "Quatre mille huit"
4 digit numbers with decimal points 1954.06 "Mille neuf cent, cinquante-quatre zéro six"
7 digit number with comma 2,000,000 "Deux virgule zero zero zero zero zero zero"
4 digit numbers with a comma 1,876 "Un vigule huite cent soixant seize"
7 digit number without comma 3000000 "Trois millions"

This section covers how the TTS engine pronounces date and time text. You can use the SSML say-as element to ensure that the TTS engine pronounces a date or time value correctly.

Note. Roman Numerals in dates are not supported.

Dates in Canada are formatted as dd/mm/yyyy.

Text Pronunciation
7/7/1977 "Sept Juillet, mille neuf cent soixant dix-sept"
1984 "Mille neuf cent quatre-vingt quatre"
Janvier 8, 2014 "Janvier huit, deux mille quatorze"
22/12/14 "vingt-deux , Décembre deux mille quatorze"

Time can be formatted in different ways. Below are examples of the different formats. In general, time is expressed in 12-hour format, with am and pm to indicate morning or evening. For official purposes 24-hour time notation is used.

  • 12:14
  • 12:14:13
  • 12:14 pm
Text Pronunciation
13:01 "Treize heures un"
1:00 "Une heure"
0:00 "minuit"
14:03:04 "quatorze heures, trois minutes et quatre secondes"

While you can use all valid XML character sequences in the range U+0000 to U+FFFF in your VoiceXML documents, character data to be processed by the TTS engine (e.g. text in prompt and audio elements) must be non-control characters in the following Unicode tables:

The following is a list of known issues related to this language:

  • Expect incorrect pronunciation of numbers if digits are separated by comma.
See Also
Speech Synthesis Markup Element Reference, Unicode Code Charts
[24]7 Inc.| Terms of Service| Privacy Policy| General Disclaimers