Synthesize speech from text

curl --request POST \
  --url http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "Hello, how are you today?",
  "model": "melo-tts-en",
  "language": "en",
  "voice": "default",
  "sample_rate": 44100,
  "output_speaker": false
}
'

import requests

url = "http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize"

payload = {
    "text": "Hello, how are you today?",
    "model": "melo-tts-en",
    "language": "en",
    "voice": "default",
    "sample_rate": 44100,
    "output_speaker": False
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    text: 'Hello, how are you today?',
    model: 'melo-tts-en',
    language: 'en',
    voice: 'default',
    sample_rate: 44100,
    output_speaker: false
  })
};

fetch('http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_PORT => "62437",
  CURLOPT_URL => "http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize",
  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' => 'Hello, how are you today?',
    'model' => 'melo-tts-en',
    'language' => 'en',
    'voice' => 'default',
    'sample_rate' => 44100,
    'output_speaker' => false
  ]),
  CURLOPT_HTTPHEADER => [
    "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 := "http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize"

	payload := strings.NewReader("{\n  \"text\": \"Hello, how are you today?\",\n  \"model\": \"melo-tts-en\",\n  \"language\": \"en\",\n  \"voice\": \"default\",\n  \"sample_rate\": 44100,\n  \"output_speaker\": false\n}")

	req, _ := http.NewRequest("POST", url, payload)

	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("http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize")
  .header("Content-Type", "application/json")
  .body("{\n  \"text\": \"Hello, how are you today?\",\n  \"model\": \"melo-tts-en\",\n  \"language\": \"en\",\n  \"voice\": \"default\",\n  \"sample_rate\": 44100,\n  \"output_speaker\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"text\": \"Hello, how are you today?\",\n  \"model\": \"melo-tts-en\",\n  \"language\": \"en\",\n  \"voice\": \"default\",\n  \"sample_rate\": 44100,\n  \"output_speaker\": false\n}"

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

"<string>"

{
  "error": {
    "message": "Invalid request, missing 'file' parameter",
    "type": "invalid_request_error",
    "param": "file",
    "code": null
  }
}

{
  "error": {
    "message": "Invalid request, missing 'file' parameter",
    "type": "invalid_request_error",
    "param": "file",
    "code": null
  }
}

Synthesize speech from text

Converts text into spoken audio using text-to-speech synthesis.

Features

Multiple voices and languages
Configurable sample rate (44100, 22050, 16000 Hz)
Automatic resampling
Streaming audio output (chunked transfer encoding)

Sample Rate

The TTS engine outputs audio at 44100 Hz by default. If you specify a different sample_rate, the audio will be automatically resampled to match your request.

Example Request

{
  "text": "Hello, how are you today?",
  "model": "melo-tts-en",
  "language": "en",
  "voice": "default",
  "sample_rate": 44100
}

Response

The response is binary PCM audio data (raw audio, not WAV format) streamed using HTTP chunked transfer encoding. To play the audio, you’ll need to convert it to WAV format using the provided pcm_to_wav.py script:

python pcm_to_wav.py speech.pcm speech.wav --rate 44100 --channels 1 --bits 16

Supported Parameters

Check model capabilities via /tts/models to see which parameters are supported:

gender: Voice gender (if supported)
style: Speaking style (if supported)
sample_rate: Output sample rate (if supported)
parameters: Additional fine-tuning options

POST

tts

synthesize

Synthesize speech from text

curl --request POST \
  --url http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "Hello, how are you today?",
  "model": "melo-tts-en",
  "language": "en",
  "voice": "default",
  "sample_rate": 44100,
  "output_speaker": false
}
'

import requests

url = "http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize"

payload = {
    "text": "Hello, how are you today?",
    "model": "melo-tts-en",
    "language": "en",
    "voice": "default",
    "sample_rate": 44100,
    "output_speaker": False
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    text: 'Hello, how are you today?',
    model: 'melo-tts-en',
    language: 'en',
    voice: 'default',
    sample_rate: 44100,
    output_speaker: false
  })
};

fetch('http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_PORT => "62437",
  CURLOPT_URL => "http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize",
  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' => 'Hello, how are you today?',
    'model' => 'melo-tts-en',
    'language' => 'en',
    'voice' => 'default',
    'sample_rate' => 44100,
    'output_speaker' => false
  ]),
  CURLOPT_HTTPHEADER => [
    "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 := "http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize"

	payload := strings.NewReader("{\n  \"text\": \"Hello, how are you today?\",\n  \"model\": \"melo-tts-en\",\n  \"language\": \"en\",\n  \"voice\": \"default\",\n  \"sample_rate\": 44100,\n  \"output_speaker\": false\n}")

	req, _ := http.NewRequest("POST", url, payload)

	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("http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize")
  .header("Content-Type", "application/json")
  .body("{\n  \"text\": \"Hello, how are you today?\",\n  \"model\": \"melo-tts-en\",\n  \"language\": \"en\",\n  \"voice\": \"default\",\n  \"sample_rate\": 44100,\n  \"output_speaker\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("http://{device-ip}:{device-port}/audio-analytics/v1/api/tts/synthesize")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"text\": \"Hello, how are you today?\",\n  \"model\": \"melo-tts-en\",\n  \"language\": \"en\",\n  \"voice\": \"default\",\n  \"sample_rate\": 44100,\n  \"output_speaker\": false\n}"

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

"<string>"

{
  "error": {
    "message": "Invalid request, missing 'file' parameter",
    "type": "invalid_request_error",
    "param": "file",
    "code": null
  }
}

{
  "error": {
    "message": "Invalid request, missing 'file' parameter",
    "type": "invalid_request_error",
    "param": "file",
    "code": null
  }
}

Body

application/json

Text-to-speech synthesis request

text

string

required

Text to synthesize into speech

Example:

"Hello, how are you today?"

model

string

required

TTS model ID

Example:

"melo-tts-en"

language

string

ISO 639-1 language code

Example:

"en"

voice

string

Voice identifier (if model supports multiple voices)

Example:

"default"

gender

enum<string>

Voice gender preference (if supported by model)

Available options:

male,

female,

neutral

Example:

"neutral"

style

string

Speaking style (if supported by model)

Example:

"neutral"

sample_rate

integer

Output sample rate in Hz (if supported by model). Audio will be resampled if different from native rate.

Example:

44100

parameters

object

Additional synthesis parameters (e.g., speaking_rate, pitch, gain)

Show child attributes

Example:

{
  "speaking_rate": "1.0",
  "pitch": "1.0",
  "gain": "0.0"
}

output_speaker

boolean

Output audio data results to speaker

Example:

false

Response

Speech synthesized successfully

Raw PCM audio data (16-bit little-endian). Not WAV — convert before playback.

List available TTS models and voices Close active text-to-speech session