Voices

List voices

curl --request GET \
  --url https://api.kova.ai/v1/tts/speakers \
  --header 'x-api-key: <api-key>'

const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};

fetch('https://api.kova.ai/v1/tts/speakers', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.kova.ai/v1/tts/speakers",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.kova.ai/v1/tts/speakers"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("x-api-key", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.kova.ai/v1/tts/speakers")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'

response = http.request(request)
puts response.read_body

GET

tts

speakers

List voices

curl --request GET \
  --url https://api.kova.ai/v1/tts/speakers \
  --header 'x-api-key: <api-key>'

const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};

fetch('https://api.kova.ai/v1/tts/speakers', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.kova.ai/v1/tts/speakers",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.kova.ai/v1/tts/speakers"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("x-api-key", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.kova.ai/v1/tts/speakers")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'

response = http.request(request)
puts response.read_body

Pass any speaker_ids value from GET /v1/tts/speakers as the voice field in your TTS requests.

The voice catalog is live and changes over time — call /v1/tts/speakers at startup rather than hardcoding ids.

Current catalog

As of the last update to this page, GET /v1/tts/speakers returns nine voices:

{"speaker_ids":["cal","owen","ash","mira","theo","tess","paul","mira_conv","ash_conv"]}

Voice	Notes
`cal`	General purpose. Used in most examples throughout these docs.
`owen`	General purpose.
`ash`	General purpose.
`mira`	General purpose.
`theo`	General purpose.
`tess`	General purpose.
`paul`	General purpose.
`mira_conv`	Conversational variant of `mira`.
`ash_conv`	Conversational variant of `ash`.

The _conv suffix marks conversational variants, tuned for dialogue rather than read-aloud prose. They’re a good starting point for voice agents.

Passing a voice that isn’t in this list returns 422 with the full valid set in the body:

{
  "error": "unknown_voice",
  "message": "Unknown voice 'nope'. Valid voices: ash, ash_conv, cal, mira, mira_conv, owen, paul, tess, theo",
  "voice": "nope",
  "valid_voices": ["ash", "ash_conv", "cal", "mira", "mira_conv", "owen", "paul", "tess", "theo"]
}

You can recover the live catalog from that valid_voices field without a separate call.

Listing voices

import os, httpx

resp = httpx.get(
    "https://api.kova.ai/v1/tts/speakers",
    headers={"x-api-key": os.environ["KOVA_API_KEY"]},
)
resp.raise_for_status()
print(resp.json()["speaker_ids"])

const resp = await fetch("https://api.kova.ai/v1/tts/speakers", {
  headers: { "x-api-key": process.env.KOVA_API_KEY! },
});
const { speaker_ids } = await resp.json();
console.log(speaker_ids);

curl https://api.kova.ai/v1/tts/speakers \
  -H "x-api-key: $KOVA_API_KEY"

The response has exactly one key, speaker_ids. The endpoint requires authentication — an unauthenticated call returns 401.

The SDKs do not currently expose a list_voices / listVoices convenience method. Use raw HTTP as above.

Picking a voice

Different voices differ in accent, age, and energy. The best way to choose is to listen to the same line through each one.

import os
from kova_tts import KovaTTSClient, AudioResponseFormat

client = KovaTTSClient(api_key=os.environ["KOVA_API_KEY"])

# Pull the live list rather than hardcoding.
import httpx
voices = httpx.get(
    "https://api.kova.ai/v1/tts/speakers",
    headers={"x-api-key": os.environ["KOVA_API_KEY"]},
).json()["speaker_ids"]

for voice in voices:
    result = client.tts(
        text="Welcome to Kova. This is what I sound like.",
        voice=voice,
        response_format=AudioResponseFormat(encoding="mp3"),
    )
    client.write_audio_file(result.audio, f"sample-{voice}.mp3")
    print(f"wrote sample-{voice}.mp3")

That writes one MP3 per voice into the working directory so you can play them back-to-back.

Generation is non-deterministic — the same text and voice produce slightly different audio on each call. That’s expected and not a sign of a misconfigured request.

Authorizations

x-api-key

string

header

required

Response

200 - application/json

Successful Response

Get started

HTTP API

WebSocket API

Integrations

SDKs

Reference

Voices

Current catalog

Listing voices

Picking a voice

Authorizations

Response

​Current catalog

​Listing voices

​Picking a voice

Authorizations

Response

Current catalog

Listing voices

Picking a voice