Elevenlabs turbo v2 Text to Speech

POST /v3/elevenlabs-tts-turbo-v2

Elevenlabs turbo v2 Text to Speech

cURL

curl --request POST \
  --url https://api.myrouter.ai/v3/elevenlabs-tts-turbo-v2 \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "text": "<string>",
  "voice_id": "<string>",
  "next_text": "<string>",
  "language_code": "<string>",
  "output_format": "<string>",
  "previous_text": "<string>",
  "use_pvc_as_ivc": true,
  "voice_settings": {
    "speed": 123,
    "style": 123,
    "stability": 123,
    "similarity_boost": 123,
    "use_speaker_boost": true
  },
  "next_request_ids": [
    {}
  ],
  "previous_request_ids": [
    {}
  ],
  "apply_text_normalization": "<string>",
  "apply_language_text_normalization": true,
  "pronunciation_dictionary_locators": [
    {
      "version_id": "<string>",
      "pronunciation_dictionary_id": "<string>"
    }
  ]
}
'

import requests

url = "https://api.myrouter.ai/v3/elevenlabs-tts-turbo-v2"

payload = {
    "seed": 123,
    "text": "<string>",
    "voice_id": "<string>",
    "next_text": "<string>",
    "language_code": "<string>",
    "output_format": "<string>",
    "previous_text": "<string>",
    "use_pvc_as_ivc": True,
    "voice_settings": {
        "speed": 123,
        "style": 123,
        "stability": 123,
        "similarity_boost": 123,
        "use_speaker_boost": True
    },
    "next_request_ids": [{}],
    "previous_request_ids": [{}],
    "apply_text_normalization": "<string>",
    "apply_language_text_normalization": True,
    "pronunciation_dictionary_locators": [
        {
            "version_id": "<string>",
            "pronunciation_dictionary_id": "<string>"
        }
    ]
}
headers = {
    "Content-Type": "<content-type>",
    "Authorization": "<authorization>"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
  body: JSON.stringify({
    seed: 123,
    text: '<string>',
    voice_id: '<string>',
    next_text: '<string>',
    language_code: '<string>',
    output_format: '<string>',
    previous_text: '<string>',
    use_pvc_as_ivc: true,
    voice_settings: {
      speed: 123,
      style: 123,
      stability: 123,
      similarity_boost: 123,
      use_speaker_boost: true
    },
    next_request_ids: [{}],
    previous_request_ids: [{}],
    apply_text_normalization: '<string>',
    apply_language_text_normalization: true,
    pronunciation_dictionary_locators: [{version_id: '<string>', pronunciation_dictionary_id: '<string>'}]
  })
};

fetch('https://api.myrouter.ai/v3/elevenlabs-tts-turbo-v2', 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.myrouter.ai/v3/elevenlabs-tts-turbo-v2",
  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([
    'seed' => 123,
    'text' => '<string>',
    'voice_id' => '<string>',
    'next_text' => '<string>',
    'language_code' => '<string>',
    'output_format' => '<string>',
    'previous_text' => '<string>',
    'use_pvc_as_ivc' => true,
    'voice_settings' => [
        'speed' => 123,
        'style' => 123,
        'stability' => 123,
        'similarity_boost' => 123,
        'use_speaker_boost' => true
    ],
    'next_request_ids' => [
        [
                
        ]
    ],
    'previous_request_ids' => [
        [
                
        ]
    ],
    'apply_text_normalization' => '<string>',
    'apply_language_text_normalization' => true,
    'pronunciation_dictionary_locators' => [
        [
                'version_id' => '<string>',
                'pronunciation_dictionary_id' => '<string>'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($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://api.myrouter.ai/v3/elevenlabs-tts-turbo-v2"

	payload := strings.NewReader("{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"voice_id\": \"<string>\",\n  \"next_text\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"output_format\": \"<string>\",\n  \"previous_text\": \"<string>\",\n  \"use_pvc_as_ivc\": true,\n  \"voice_settings\": {\n    \"speed\": 123,\n    \"style\": 123,\n    \"stability\": 123,\n    \"similarity_boost\": 123,\n    \"use_speaker_boost\": true\n  },\n  \"next_request_ids\": [\n    {}\n  ],\n  \"previous_request_ids\": [\n    {}\n  ],\n  \"apply_text_normalization\": \"<string>\",\n  \"apply_language_text_normalization\": true,\n  \"pronunciation_dictionary_locators\": [\n    {\n      \"version_id\": \"<string>\",\n      \"pronunciation_dictionary_id\": \"<string>\"\n    }\n  ]\n}")

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

	req.Header.Add("Content-Type", "<content-type>")
	req.Header.Add("Authorization", "<authorization>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.myrouter.ai/v3/elevenlabs-tts-turbo-v2")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"voice_id\": \"<string>\",\n  \"next_text\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"output_format\": \"<string>\",\n  \"previous_text\": \"<string>\",\n  \"use_pvc_as_ivc\": true,\n  \"voice_settings\": {\n    \"speed\": 123,\n    \"style\": 123,\n    \"stability\": 123,\n    \"similarity_boost\": 123,\n    \"use_speaker_boost\": true\n  },\n  \"next_request_ids\": [\n    {}\n  ],\n  \"previous_request_ids\": [\n    {}\n  ],\n  \"apply_text_normalization\": \"<string>\",\n  \"apply_language_text_normalization\": true,\n  \"pronunciation_dictionary_locators\": [\n    {\n      \"version_id\": \"<string>\",\n      \"pronunciation_dictionary_id\": \"<string>\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.myrouter.ai/v3/elevenlabs-tts-turbo-v2")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"voice_id\": \"<string>\",\n  \"next_text\": \"<string>\",\n  \"language_code\": \"<string>\",\n  \"output_format\": \"<string>\",\n  \"previous_text\": \"<string>\",\n  \"use_pvc_as_ivc\": true,\n  \"voice_settings\": {\n    \"speed\": 123,\n    \"style\": 123,\n    \"stability\": 123,\n    \"similarity_boost\": 123,\n    \"use_speaker_boost\": true\n  },\n  \"next_request_ids\": [\n    {}\n  ],\n  \"previous_request_ids\": [\n    {}\n  ],\n  \"apply_text_normalization\": \"<string>\",\n  \"apply_language_text_normalization\": true,\n  \"pronunciation_dictionary_locators\": [\n    {\n      \"version_id\": \"<string>\",\n      \"pronunciation_dictionary_id\": \"<string>\"\n    }\n  ]\n}"

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

Converts text to speech using your chosen voice and returns audio.

Request Headers

Content-Type · string · required

Enum: application/json

Authorization · string · required

Bearer authentication format: Bearer {{API Key}}.

Request Body

seed · integer

If specified, the system will attempt to sample deterministically. Repeated requests with the same seed and parameters should return the same result, but full determinism is not guaranteed.

Range: [0, 4294967295]

text · string · required

The text to convert to speech.

voice_id · string · required

The voice ID to use.

next_text · string

The text that comes after the current request text. Used to improve speech continuity when concatenating multiple generations.

language_code · string

Language code (ISO 639-1) used for the model and text normalization. An error will be returned if the model does not support this language code.

output_format · string · default: "mp3_44100_128"

Output format for the generated audio. Format is codec_sample_rate_bitrate. The 192kbps bitrate for MP3 requires a Creator or higher account; the 44.1kHz sample rate for PCM requires a Pro or higher account.

Possible values: mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192

previous_text · string

The text that comes before the current request text. Used to improve speech continuity when concatenating multiple generations.

use_pvc_as_ivc · boolean · default: false

If true, uses the IVC version of the voice instead of the PVC version. This is a temporary workaround for higher latency with the PVC version.

voice_settings · object

Hide properties

speed · number · default: 1

Adjusts the speed of the voice. 1.0 is the default speed; values below 1.0 slow down the speech, values above 1.0 speed it up.

style · number · default: 0

Controls the exaggeration of the voice style. Attempts to amplify the style of the original speaker. Setting to a non-zero value consumes more compute resources and may increase latency.

stability · number

Controls the stability of voice generation and the randomness between each generation. Lower values produce a wider emotional range; higher values may result in a more monotone voice.

similarity_boost · number

Controls how closely the AI attempts to replicate the original voice.

use_speaker_boost · boolean · default: true

Enhances similarity to the original speaker. Requires slightly more compute and increases latency.

next_request_ids · array

List of request_ids for subsequent samples. Used to maintain speech continuity when regenerating samples. Up to 3 request_ids can be provided.

Array length: 0 - 3

previous_request_ids · array

List of request_ids for previously generated samples before the current generation. Can be used to improve speech continuity. Up to 3 request_ids can be provided.

Array length: 0 - 3

apply_text_normalization · string · default: "auto"

Controls text normalization. ‘auto’ lets the system decide, ‘on’ always normalizes, ‘off’ skips normalization.

Possible values: auto, on, off

apply_language_text_normalization · boolean · default: false

Controls language-specific text normalization for certain supported languages to achieve more natural pronunciation. Warning: may significantly increase latency. Currently only supports Japanese.

pronunciation_dictionary_locators · array

List of pronunciation dictionary locators (id, version_id) to apply to the text. Applied in order. Up to 3 locators per request.

Array length: 0 - 3

Hide properties

version_id · string

The ID of the pronunciation dictionary version. If not specified, the latest version will be used.

pronunciation_dictionary_id · string · required

The ID of the pronunciation dictionary.

Response

The generated audio file

Format: binary