Voice model parameter selection

Filtering by Parameters

One of the challenges with a catalogue of over 180 voices is the problem of choice. This presents is a discovery problem, very few users want to filter through 180 plus voices!
So to deal with this we introduced parameters. Parameters are added and updated regularly by our content team.

List of Parameters:

  • provider (string) - Try one of: google, polly, azure, msnr
  • providerFullName (string) - Try with one of: amazon polly, google, microsoft azure, msnr
  • language (string) - Try with one of: english, spanish, french, german
  • accent (string) - Try with one of: american, british, neutral, portuguese/brazilian, american soft, mexican, australian
  • gender (string) - Try with one of: male, female
  • ageBracket (string) - Try with one of: adult, child, senior
  • tags (string) - Try with one or more (separated by commas) of: steady, confident, balanced, informative, serious, instructional, slow, storytelling, calm, clear, deep, formal, sad, thin, fast, upbeat, fun, energetic, tense, very fast, flat, low pitched, high pitched, low-pitched, sing-y, cooperative, kind, stable, monotonous, neutral, responsible, business man, straight to the point, knowledgeable, focused, newscastery, newsreader, interviewer, reliable, friendly, welcoming, good for handing out information, slightly friendly
  • industryExamples (string) - Try with one or more of: fitness, business, commercial, fashion, travel, audiobook, faith, health industry, commercial, real estate, kids entertainment, games, customer service, education, storytelling, entertainment, kids, education audiobook

See more here

Examples

Let's consider a few examples

Example 1

For example. What if I have a use case where I want an English voice, and I want to look at steady and fun voices

# Specify only English voices with the tags - steady and fun
steady_and_fun_english_voices = aflr.Voice().list(language="english",tags="steady, fun") 
print(steady_and_fun_english_voices)

Example 2

You may be working on a kids toy application. Therefore you'll need to listen to voices that are good at storytelling or kids entertainment. You would simply run the following code.

# We want to try the voices that are selected for kids entertainment
kids_entertainment = aflr.Voice().list(language="english",industryExamples="kids entertainment") 
print(kids_entertainment)

Example 3

You may be working on an enterprise program - for example building onboarding or training software for Forbes 500 companies. These voices need to be quite serious. You would simply run the following code.

# We want to try the voices that are selected for education
education_voices = aflr.Voice().list(language="english",industryExamples="education") 
print(education_voices)

Did this page help you?