How Text-to-Speech Prayers Work

Text-To-Speech, or TTS as it is known, is the ability to convert text into audible speech. TTS allows a computer to convert your written words into phonetic sounds that resemble a human voice.

To convert your words into sound, TTS systems first looks at your text and decide how it should be spoken, that is, how each word should be pronounced, what length and pitch to give each syllable, etc. The system then does its best to create audio that matches the written text.

TTS systems have little or no understanding of the text being read. They use resources such as rules, lists and dictionaries to make very sophisticated "guesses" about how a piece of text should be read. While general performance can be quite good, some decisions are intrinsically hard to make without some level of understanding. For example, the word "bass" in the phrases "bass drum" or "bass boat". Intonation depends in many cases on the writer's intention, which often cannot be inferred in short texts even by human readers. As a result, TTS systems will occasionally make mistakes and may get fooled by certain texts. These are challenging problems for all TTS systems, and we continue to improve ours.

The type of TTS system we use is called "concatenative". This type of system utilizes a voice database containing words recorded by a real human speaker. Small chunks of the recordings are pieced together to create new sentences containing words that may never have been recorded. Further, we do "unit selection" synthesis. This means that we employ a large voice databases and do intelligent searches, on-the-fly, to find chunks in the voice database that best match the requested sentences.

At present we only support English text-to-speech. We hope to offer additional languages in the future.

Have a Listen and call the Holy Land Internet Prayer Gateway +972 3 565 1848 to a voice recorded prayer.