Back

Synthetic voices or TTS, computerized voice
TTS Synthetic Voices NEW!

TTS is an audio technology in constant development that can offer a straight-forward and non-expensive solution for short vocal messages.

Text to Speech converts any written words into a humanoid voice, utilising a database or memory composed of many audio narrations recorded by real voice talents. The audio is then segmented phonetically and fed into a computer. Through a complex algorithm, the computer relates and applies the sounds to written words and expressions (a script). The result is a synthetic voice not sensitive to context with timing and intonation (prosody) still open to perfection.

TTS is a low-cost and fast delivery option now offered by PrimeVoices in a limited number of languages.

It is best suited for short audio/animated videos with no on-screen actors.

It is not recommended for long audio or for content with on-screen characters.

Not all TTS are equal and this is still an evolving technology. Prime Group has selected high standard algorithms to provide convincing high-quality audio. We are also able to work with SSML tags to enhance final product.

Online Casting

Search by language

OUPS ! NO RESULT ON THAT SEARCH, PLEASE TRY AGAIN

Listen to your samples below

PROS
  • Affordable - starting at 0.10 USD per recorded word
  • Scalable - sourcing from a machine
  • Fast - thanks to our efficient pipelines and workflow
CONS
  • Audio glitches (need post-prod to fix it)
  • Intonation patterns sometimes not natural
  • Unable to read foreign names, places or brands (need post-prod intervention)
  • Loses listener’s attention for longer audio

Languages Available

North America
  • Canadian French
  • US English
  • US Spanish
  • MX Spanish
Europe
  • ES Spanish
  • UK English
  • French
  • Italian
  • Portuguese
  • Danish
  • Greek
  • German
  • Ukrainian
  • Icelandic
  • Dutch
  • Polish
  • Swedish
  • Norwegian
  • Romanian
  • Hungarian
  • Slovak
  • Finnish
  • Russian
  • Czech
Asia
  • Turkish
  • Japanese
  • Mandarin Chinese
  • Vietnamese
  • Korean
  • Indonesian
  • Indian English
  • Hindi
  • Bengali
  • Tamil
  • Gujarati
  • Kannada
  • Malayalam
  • Filipino
South America
  • Spanish
  • Brazilian Portuguese
Africa
  • Arabic
Oceania
  • Australian English

Price

Non - Timed
Audio

Minimum Fee 100 USD par voice
At 0.10 USD per recorded word,
or 100 USD for 1,000 words.

Timed - Audio
(On pictures)

Minimum Fee 200 USD par voice
At 0.20 USD per recorded word,
or 200 USD for 1,000 words.

Extra Costs
(Optional)

Post-prod to remove glitches
and improve audio at 50 USD
per working hour.