Hiring voice talent for voiceover work can be expensive, particularly if you have to do it multiple times for different languages. Many of the world’s information technology giants offer text-to-voice or text-to-speech services which turn typed text into audible speech or voice. These high-quality audio files can be used to narrate software, both in standard operation and help sections, accompany training videos, or even act as voice-over tracks for videos.
While text-to-speech or text-to-voice technology is reasonably mature, the end results are not always perfect, and the scriptwriter has no control over how the voice in the file sounds. Company-X built a text-to-voice editor taking advantage of this technology that allows the user to make the voice sound almost like natural speech.
Speech Synthesis Markup Language (SSML) tags control emphasis, pitch, speed and tone. A variety of male and female voices and languages are available. The text-to-voice or text-to-speech editor builds a pronunciation library of acronyms and specialist terminology. With this editing tool, the world leader in milking equipment and dairy solutions, DeLaval International, has transformed the manual voice translation process internationally into a fully automated digital process.
The Company-X text-to-voice editor removed the need for DeLaval to book voiceover artists, directors, sound technicians and recording studios for six languages. Instead of a half-day block of recording costing tens of thousands of dollars per language, the audio files were produced in minutes at 10 per cent of the cost. DeLaval’s production staff can edit and resynthesize the result at any time using SSML tags. If the material needs to be updated the user can replace the entire text and produce the voice file within a few mouse clicks.
Apart from the automated voice file generation, the text-to-voice or text-to-speech editor created a translation platform significantly reducing the time to deliver translated content to the global market. The text-to-voice or text-to-speech tool delivers consistent results across all regions.
