Can I use SSML in Soundly Voice Designer?

The Soundly Voice Designer supports several SSML tags to enable more natural and expressive speech. Please note that it’s not guaranteed that all voices will support all tags.

The supported tags include:

Emphasis tag: Used to add emphasis to a word or phrase.

To use the emphasis tag with Soundly, you can set the level attribute to “strong” or “moderate” to indicate the degree of emphasis. Here’s an example:

I <emphasis level="strong">really</emphasis> enjoyed the movie.

In this example, the emphasis tag is used to add strong emphasis to the word “really”.

Attributes level: The degree of emphasis. The supported values are “strong” for strong emphasis and “moderate” for moderate emphasis.

Prosody tag: Used to adjust the pitch, rate, and volume of speech.

To use the prosody tag with Soundly, you can adjust the pitch, rate, and volume of speech using the pitch, rate, and volume attributes. Here’s an example:

She spoke <prosody pitch="+50%">loudly</prosody> and <prosody rate="slow">slowly</prosody>

In this example, the prosody tag is used to increase the pitch and slow down the rate of speech.

Attributes: pitch: The pitch adjustment, specified as a percentage relative to the baseline pitch. A positive value raises the pitch, and a negative value lowers the pitch. rate: The rate adjustment, specified as a percentage relative to the baseline rate. A positive value increases the rate, and a negative value decreases the rate. volume: The volume adjustment, specified as a percentage relative to the baseline volume. A positive value increases the volume, and a negative value decreases the volume.

Say-as tag To use the say-as tag with Soundly, you can specify the interpretation using the interpret-as attribute. Here’s an example:

My phone number is <say-as interpret-as="telephone">555-1234</say-as>

In this example, the say-as tag is used to specify that the sequence of digits “555-1234” should be spoken as a telephone number.

Attributes: interpret-as: The interpretation of the content. The supported values are “cardinal” for a cardinal number, “ordinal” for an ordinal number, “characters” for individual characters, “fraction” for a fraction, “expletive” for an expletive, “spell-out” for spelling out the content, “date” for a date, “time” for a time, “telephone” for a telephone number, “address” for an address, “interjection” for an interjection, and “verbatim” for verbatim content.

Break tag: Used to insert a pause in speech.

To use the break tag with Soundly, you can set the strength attribute to “none”, “x-weak”, “weak”, “medium”, “strong”, or “x-strong” to indicate the strength of the pause. Here’s an example:

The train arrives at <break strength="strong"/> 10:30.

In this example, the break tag is used to insert a strong pause after the word “arrives”.

Attributes time: The duration of the pause in milliseconds. The value can be a decimal number, such as “250ms” for a 250 millisecond pause.

Phoneme tag: Used to specify the pronunciation of a word or a sequence of phonemes. To use the phoneme tag with Soundly, you can specify the phoneme sequence using the ph attribute and the alphabet using the alphabet attribute. Here’s an example:

The word <phoneme alphabet="ipa" ph="dɪˈfɪnɪtli">definitely</phoneme> is often misspelled.

In this example, the phoneme tag is used to specify the IPA pronunciation of the word “definitely”.

Attributes: alphabet: The phonetic alphabet used to specify the phoneme sequence. The supported values are “ipa” for the International Phonetic Alphabet, “x-sampa” for the Extended Speech Assessment Methods Phonetic Alphabet, and “upu” for the Universal Phonemic Alphabet. ph: The phoneme sequence to be pronounced.