FAQ - General
What does Odiogo do?
How does Odiogo convert text articles into sound files?
How good is Odiogo's sound quality?
How does Text to Speech (TTS) work?
How big are the audio files generated by Odiogo?
Which languages are supported by Odiogo?
What does Odiogo do? Odiogo technology provides an intelligent and automated bridge linking text-content providers and bloggers with
the vast community of users of audio-enabled mobile devices. Odiogo monitors the feeds to be podcast; whenever
a change is spotted, Odiogo processes the new content, automatically excluding "non-content" parts of the page
(such as links, images, ads, etc.) to ensure that they will not be included in the generated MP3 file. ^ top
How does Odiogo convert text articles into sound files? Odiogo uses artificial intelligence technology called text-to-speech (TTS) to convert textual content into
spoken words. Odiogo's linguistic teams are constantly improving the quality of the automatically-produced podcasts,
teaching the TTS engine how to pronounce new words such as products, companies, foreign names, or new abbreviations. ^ top
How good is Odiogo's sound quality? Even though the files are computer-generated, Odiogo provides high quality sound and a true-to-life human-like voice.
Here is a sample. ^ top
How does Text to Speech (TTS) work? TTS engines generally work in three steps: normalization, phonetization and speech synthesis. In the normalization phase,
special expressions like abbreviations, email addresses or URLs are written out in full.
In the phonetization phase, the correct phonetic transcription of a word is then looked up from a pronunciation dictionary
(i.e., glossary). For words absent from the dictionary, the pronunciation is automatically computed using
spelling-to-pronunciation rules. Homographs like 'record' or 'lives' are disambiguated by their part of speech
(verb vs. noun).
Finally, the speech synthesis phase uses the phonetic information and prosodic cues (pitch, duration) to produce the
actual audio.
Odiogo's linguistic team keeps improving the normalization and phonetization processes. ^ top
How big are the audio files generated by Odiogo? The audio files produced by Odiogo are very small: the average news item 'weighs' 1 MB. In other words,
you can store approximately 500 articles on a 512 MB MP3 player. The podcast feature
of iTunes or Juice will automatically manage the deletion of old MP3 files. There is therefore no risk of
overloading the memory of your mobile device. ^ top
Which languages are supported by Odiogo? At this time Odiogo supports articles written in English only. However, we are planning to support other
major European and Asian languages in the near future. Should you have an immediate need in a particular
language, please don't hesitate to contact us. ^ top
|