Custom voices


Differentiate yourself with an  exclusive, unique voice created with Acapela Voice Factory.

Designed to perform your voice branding through any audio touch point, this highly competitive solution provides you with a very natural and pleasant synthetic voice, for enhancing your brand identity, increasing consumer confidence and extending your business into new markets and services.

The Acapela Voice Factory is the result of in-depth research into recording, segmentation and fine-tuning methods used in the text-to-speech production process. Using expertise and industry insight, the Acapela Voice Factory has been designed to develop natural, exclusive voices at an unbeatable price – 2 to 10 times less expensive than other solutions currently available on the market.

Perform you own synthetic Voice Persona

This solution, which can create up to one hundred new voices every year, accurately reproduces a given voice (including celebrity ones) in a short space of time. Voices are initially recorded in the studio with the selected speaker and are then analysed, sliced and orchestrated to develop a synthetic voice that remains true to the original recording.

Acapela Voice Factory allows companies to enrich simple visual branding with an effective audio counterpart.

Create your own voice, step by step

Your Acapela voice is available in 3 different versions – providing a step by step
validation process, enabling you to shape perfectly the voice you need.

Hear samples in the 3 different versions

Sample 1:

      Quality 1

Quality 2

Quality 3

Sample 2 :

Quality 1

Quality 2

Quality 3

Quality 1 – “Voice at First Sight”

To be used for :
> Evaluation, Prototyping, Beta-testing, Proof of Concept
> Specific Applications such as character based or domain limited

An automatically generated voice produced from a minimal acoustic database of recordings. It delivers a first version of your voice within two weeks. This quality may not always be consistent but is customized through 10 % application specific recordings and is completely usable in evaluation, prototyping, beta testing and domain text to speech applications. The price and the short delivery time also open up new perspectives in the field of multiple voice applications.

Quality 2 – “Small Talk Voice”

To be used for:
> Evaluation, Prototyping, Beta-testing, Proof of Concept
> Extended Applications

Based on the “Voice at First Sight” with manual fine tuning and refining.
A second version of the customized voice, based on the recordings of the “Voice at First Sight” with an increased and totally consistent quality throughout the database due to expert manual fine-tuning and refining. This operation requires only 3 additional weeks.

Quality 3 – “High Quality Voice”

Based on the “Small Talk Voice” with additional recordings.
This version equals the highest quality standard of our generic voices. Based on extended recordings of the “Small Talk Voice”, manually verified, enhanced, refined and optimized with high level tools and finally put through a quality control process, this voice has the same level of quality as our HQ generic voices – even better in its domain specification. This step takes 2 months more if based on the “Small Talk Voice”.

 Acapela Voice Factory roadmap

Q1 – “Voice at First Sight”  2 to 3 weeks

Q2 – “Small Talk”              5 to 6 weeks

Q3 – “High Quality”           3 months

With Acapela Voice Factory, Text-To-Speech solutions become much more than just technology – they enrich the capacity of applications, enabling companies from all sectors to reinforce their corporate branding.


print print