curl --request POST \
--url https://dev.voice.ai/api/v1/tts/speech \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"text": "<string>",
"voice_id": "<string>",
"audio_format": "mp3",
"temperature": 1,
"top_p": 0.8,
"language": "en",
"dictionary_id": "<string>",
"dictionary_version": 2
}
'import requests
url = "https://dev.voice.ai/api/v1/tts/speech"
payload = {
"text": "<string>",
"voice_id": "<string>",
"audio_format": "mp3",
"temperature": 1,
"top_p": 0.8,
"language": "en",
"dictionary_id": "<string>",
"dictionary_version": 2
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
text: '<string>',
voice_id: '<string>',
audio_format: 'mp3',
temperature: 1,
top_p: 0.8,
language: 'en',
dictionary_id: '<string>',
dictionary_version: 2
})
};
fetch('https://dev.voice.ai/api/v1/tts/speech', 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://dev.voice.ai/api/v1/tts/speech",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'text' => '<string>',
'voice_id' => '<string>',
'audio_format' => 'mp3',
'temperature' => 1,
'top_p' => 0.8,
'language' => 'en',
'dictionary_id' => '<string>',
'dictionary_version' => 2
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://dev.voice.ai/api/v1/tts/speech"
payload := strings.NewReader("{\n \"text\": \"<string>\",\n \"voice_id\": \"<string>\",\n \"audio_format\": \"mp3\",\n \"temperature\": 1,\n \"top_p\": 0.8,\n \"language\": \"en\",\n \"dictionary_id\": \"<string>\",\n \"dictionary_version\": 2\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://dev.voice.ai/api/v1/tts/speech")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"text\": \"<string>\",\n \"voice_id\": \"<string>\",\n \"audio_format\": \"mp3\",\n \"temperature\": 1,\n \"top_p\": 0.8,\n \"language\": \"en\",\n \"dictionary_id\": \"<string>\",\n \"dictionary_version\": 2\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://dev.voice.ai/api/v1/tts/speech")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"text\": \"<string>\",\n \"voice_id\": \"<string>\",\n \"audio_format\": \"mp3\",\n \"temperature\": 1,\n \"top_p\": 0.8,\n \"language\": \"en\",\n \"dictionary_id\": \"<string>\",\n \"dictionary_version\": 2\n}"
response = http.request(request)
puts response.read_body"<string>"{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}Generate Speech
Generate speech from text. If voice_id is provided, uses that voice; otherwise uses the default built-in voice. Returns complete audio file. Synchronous endpoint - blocks until generation completes.
curl --request POST \
--url https://dev.voice.ai/api/v1/tts/speech \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"text": "<string>",
"voice_id": "<string>",
"audio_format": "mp3",
"temperature": 1,
"top_p": 0.8,
"language": "en",
"dictionary_id": "<string>",
"dictionary_version": 2
}
'import requests
url = "https://dev.voice.ai/api/v1/tts/speech"
payload = {
"text": "<string>",
"voice_id": "<string>",
"audio_format": "mp3",
"temperature": 1,
"top_p": 0.8,
"language": "en",
"dictionary_id": "<string>",
"dictionary_version": 2
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
text: '<string>',
voice_id: '<string>',
audio_format: 'mp3',
temperature: 1,
top_p: 0.8,
language: 'en',
dictionary_id: '<string>',
dictionary_version: 2
})
};
fetch('https://dev.voice.ai/api/v1/tts/speech', 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://dev.voice.ai/api/v1/tts/speech",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'text' => '<string>',
'voice_id' => '<string>',
'audio_format' => 'mp3',
'temperature' => 1,
'top_p' => 0.8,
'language' => 'en',
'dictionary_id' => '<string>',
'dictionary_version' => 2
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://dev.voice.ai/api/v1/tts/speech"
payload := strings.NewReader("{\n \"text\": \"<string>\",\n \"voice_id\": \"<string>\",\n \"audio_format\": \"mp3\",\n \"temperature\": 1,\n \"top_p\": 0.8,\n \"language\": \"en\",\n \"dictionary_id\": \"<string>\",\n \"dictionary_version\": 2\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://dev.voice.ai/api/v1/tts/speech")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"text\": \"<string>\",\n \"voice_id\": \"<string>\",\n \"audio_format\": \"mp3\",\n \"temperature\": 1,\n \"top_p\": 0.8,\n \"language\": \"en\",\n \"dictionary_id\": \"<string>\",\n \"dictionary_version\": 2\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://dev.voice.ai/api/v1/tts/speech")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"text\": \"<string>\",\n \"voice_id\": \"<string>\",\n \"audio_format\": \"mp3\",\n \"temperature\": 1,\n \"top_p\": 0.8,\n \"language\": \"en\",\n \"dictionary_id\": \"<string>\",\n \"dictionary_version\": 2\n}"
response = http.request(request)
puts response.read_body"<string>"{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}{
"error": "<string>",
"detail": "<string>",
"code": "<string>"
}Authorizations
Bearer token authentication. Use your API key as the bearer token. Format: Authorization: Bearer
Body
The text to generate speech for. Supports inline spelling markup such as [SPELL:BX42] to spell acronyms, names, or codes character by character.
Voice ID to use. Omit to use the default built-in voice.
Audio output format (32kHz sample rate)
mp3, wav, pcm, alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, ulaw_8000, wav_16000, wav_22050, wav_24000 Sampling temperature (0.0-2.0)
0 <= x <= 2Nucleus sampling parameter (0.0-1.0)
0 <= x <= 1TTS model to use. If not provided, automatically selected based on language. English uses non-multilingual models; other languages use multilingual models.
voiceai-tts-v1-latest, voiceai-tts-v1-2026-02-10, voiceai-tts-multilingual-v1-latest, voiceai-tts-multilingual-v1-2026-02-10 Language code (ISO 639-1 format)
en, ca, sv, es, fr, de, it, pt, pl, ru, nl Optional managed pronunciation dictionary identifier.
Optional managed dictionary version. Defaults to latest when omitted.
x >= 1Response
Successful Response - Returns binary audio file (32kHz sample rate)
MP3 audio file (32kHz sample rate, compressed)