Skip to content
AderraAderraAderra DocsBeta

List speech models

GET
/v1/audio/models
curl --request GET \
  --url https://api.aderra.ai/v1/audio/models \
  --header 'Authorization: Bearer <token>'

The speech model and what it accepts: its languages, response formats (with the characters each takes, and the sample rate of pcm and wav), speed range, limits, price per 1,000 billable characters (in credits; 1,000 credits = $1), and how many voices have each filter value. Build language, format and voice-filter pickers from it.

Any Aderra key (API or terminal) may call it, and it is free: nothing is billed. Guide: https://aderra.ai/docs/api/text-to-speech/#read-the-model-from-code

Authorizations

Section titled “Authorizations”

Responses

Section titled “Responses”

200

Section titled “200”

The speech models (one today, aderra-voice-1).

Media typeapplication/json
object
object
required
string
Allowed value: list
data
required
Array<object>
object
id
required
string
object
required
string
Allowed value: model
type
required
string
Allowed value: text_to_speech
endpoint
required
string
voices
required

How many voices the model has.

integer
voice_filters
required

For each GET /v1/audio/voices filter, every value in use and how many voices have it.

object
gender
object
key
additional properties
integer
age
object
key
additional properties
integer
accent
object
key
additional properties
integer
use_case
object
key
additional properties
integer
style
object
key
additional properties
integer
languages
required

The supported languages, sorted by English name.

Array<object>
object
code
required

ISO 639-1 code, the value of language.

string
name
required
string
response_formats
required
Array<object>
object
format
required
string
Allowed values: mp3 aac pcm wav opus flac
content_type
required
string
max_characters
required

Billable characters a request takes in this format (4,096, or one 900-character chunk for formats that cannot be joined).

integer
sample_rate

pcm and wav only.

integer
channels

pcm and wav only.

integer
bits_per_sample

pcm and wav only.

integer
default_format
required
string
speed
required
object
min
required
number
max
required
number
default
required
number
max_characters
required

Billable characters per request (Chinese, Japanese and Korean characters count 3).

integer
chunk_characters
required

Longer text is spoken in chunks of up to this many billable characters, split at sentence ends, and joined.

integer
streaming
required

The audio is streamed as it is generated.

boolean
per_thousand_characters
required

The price per 1,000 billable characters, in credits (1,000 credits = $1), as an exact decimal string.

string

Example 

{
  "object": "list",
  "data": [
    {
      "id": "aderra-voice-1",
      "object": "model",
      "type": "text_to_speech",
      "endpoint": "/v1/audio/speech",
      "voices": 200,
      "voice_filters": {
        "gender": {
          "male": 119,
          "female": 81
        },
        "age": {
          "middle_aged": 119,
          "young": 74,
          "old": 7
        }
      },
      "languages": [
        {
          "code": "af",
          "name": "Afrikaans"
        }
      ],
      "response_formats": [
        {
          "format": "mp3",
          "content_type": "audio/mpeg",
          "max_characters": 4096,
          "sample_rate": 24000,
          "channels": 1,
          "bits_per_sample": 16
        }
      ],
      "default_format": "mp3",
      "speed": {
        "min": 0.7,
        "max": 1.3,
        "default": 1
      },
      "max_characters": 4096,
      "chunk_characters": 900,
      "streaming": true,
      "per_thousand_characters": "30"
    }
  ]
}

401

Section titled “401”

The key is missing, unknown or revoked: authentication_error / unauthorized.

Media typeapplication/json
object
error
required
object
type
string
param

The request field at fault, when there is one (speech).

string | null
code

The machine-readable reason. A string, except on upstream_error where it is the upstream HTTP status.

One of:
string
message
string

Example 

{
  "error": {
    "message": "Send an Aderra API key as a Bearer token.",
    "type": "authentication_error",
    "param": null,
    "code": "unauthorized"
  }
}