GET
/
models
curl --location --request GET 'https://api.revocalize.ai/models'
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <token>'

{
  "models": [
    {
      id: "andra",
      name: "Andra",
      gender: "female",
      age: "adult",
      description: "Popular pop singer with a powerful and dynamic vocal range. Her voice is characterized by its soulful quality, agility, and emotive expressiveness.",
      base_language: "en",
      traits: ["nasal", "powerful", "emotive", "dynamic", "soulful"],
      genre: "pop"
      voice_type: "tenor",
      vocal_range: {
        min: "C3",
        max: "C7",
      }
    },
    {
      id: "smiley",
      name: "Smiley",
      gender: "male",
      age: "young adult",
      description: "Romanian musician and producer known for his smooth and versatile vocal style, which ranges from tender and emotive to powerful and dynamic.",
      base_language: "ro",
      traits: ["smooth", "versatile", "emotive", "dynamic", "expressive"],
      genre: "r&b",
      voice_type: "bass",
      vocal_range: {
        min: "E2",
        max: "E4",
      }
    }
  ]
}

​
Response

models
array

The array of available AI voice models for your Revocalize account.

id
strng

A unique identifier for each AI voice model. This is the value that should be used in the voice_model parameter of the Voice Synthesis API.

name
string

The name of the artist or musician that the AI voice model is based on.

gender
"male" | "female"

The gender of the AI voice model.

age
"child" | "young adult" | "adult"

The age category of the AI voice model.

description
string

A brief description of the AI voice model’s characteristics.

base_language
string

The base language of the AI voice model, in ISO 639-1 format.

traits
array

An array of traits that describe the AI voice model’s vocal qualities.

genre
string

The genre that the AI voice model is best suited for. Possible values are:

  1. pop
  2. rock
  3. hip-hop
  4. r&b
  5. country
  6. jazz
  7. classical
  8. electronic
  9. world
  10. other
voice_type
string

The voice type of the AI voice model. Possible values are: soprano, mezzo-soprano, alto, tenor, baritone, bass.

vocal_range
object

An object containing the minimum and maximum vocal range of the AI voice model.

Check Task StatusCreate Model