Speakers

Overview

Destined Voice provides access to 10,000+ consented speakers with diverse demographics. Each speaker has unique voice characteristics captured across multiple dimensions.

Speaker Characteristics

We capture rich metadata for each speaker:

Category	Examples
Demographics	`gender`, `age_range`, `ancestry`, `skin_tone`
Location	`region`, `native_language`, `how_learn_english`
Background	`profession`, `education_level`
Voice	`voice_conditions`, `accent`

Filtering Speakers

Use query parameters to find the perfect voice:

const speakers = await client.speakers.listSpeakersV1SpeakersGet({
  gender: "Female",       // Male, Female, Non-binary
  region: "Georgia",      // US state or country
  ageRange: "25-34",      // Age bracket
  limit: 20,
  offset: 0,
});

Speaker Object

Each speaker includes:

{
  "id": "abc123-def456",
  "gender": "Female",
  "age_range": "25-34",
  "region": "Georgia",
  "native_language": "English",
  "ancestry": "African American",
  "profession": "Teacher",
  "education_level": "Bachelor's Degree",
  "voice_conditions": "None",
  ...
}

Best Practices

Choose consistent voices

For conversational AI or audiobooks, use the same speaker throughout to maintain consistency.

Match accent to content

Select speakers whose accent matches your target audience or content region.

Preview before generating

Use the sample_audio_url to preview a speaker’s voice before generating content.

Cache speaker IDs

Store speaker IDs for voices you use frequently to avoid repeated lookups.

Authentication TTS Generation

Get Started

Core Concepts

SDKs

Overview

Speaker Characteristics

Filtering Speakers

Speaker Object

Best Practices

​Overview

​Speaker Characteristics

​Filtering Speakers

​Speaker Object

​Best Practices

Overview

Speaker Characteristics

Filtering Speakers

Speaker Object

Best Practices