ElevenLabs Text-to-Speech Flash V2

curl --request POST \
  --url https://api.highwayapi.ai/v3/elevenlabs-tts-flash-v2 \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "text": "<string>",
  "stream": true,
  "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": [
    "<string>"
  ],
  "previous_request_ids": [
    "<string>"
  ],
  "apply_text_normalization": "<string>",
  "apply_language_text_normalization": true,
  "pronunciation_dictionary_locators": [
    {
      "version_id": "<string>",
      "pronunciation_dictionary_id": "<string>"
    }
  ]
}
'

import requests

url = "https://api.highwayapi.ai/v3/elevenlabs-tts-flash-v2"

payload = {
    "seed": 123,
    "text": "<string>",
    "stream": True,
    "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": ["<string>"],
    "previous_request_ids": ["<string>"],
    "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>',
    stream: true,
    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: ['<string>'],
    previous_request_ids: ['<string>'],
    apply_text_normalization: '<string>',
    apply_language_text_normalization: true,
    pronunciation_dictionary_locators: [{version_id: '<string>', pronunciation_dictionary_id: '<string>'}]
  })
};

fetch('https://api.highwayapi.ai/v3/elevenlabs-tts-flash-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.highwayapi.ai/v3/elevenlabs-tts-flash-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>',
    'stream' => true,
    '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' => [
        '<string>'
    ],
    'previous_request_ids' => [
        '<string>'
    ],
    '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.highwayapi.ai/v3/elevenlabs-tts-flash-v2"

	payload := strings.NewReader("{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"stream\": true,\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    \"<string>\"\n  ],\n  \"previous_request_ids\": [\n    \"<string>\"\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.highwayapi.ai/v3/elevenlabs-tts-flash-v2")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"stream\": true,\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    \"<string>\"\n  ],\n  \"previous_request_ids\": [\n    \"<string>\"\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.highwayapi.ai/v3/elevenlabs-tts-flash-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  \"stream\": true,\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    \"<string>\"\n  ],\n  \"previous_request_ids\": [\n    \"<string>\"\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

POST

elevenlabs-tts-flash-v2

ElevenLabs Text-to-Speech Flash V2

curl --request POST \
  --url https://api.highwayapi.ai/v3/elevenlabs-tts-flash-v2 \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "text": "<string>",
  "stream": true,
  "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": [
    "<string>"
  ],
  "previous_request_ids": [
    "<string>"
  ],
  "apply_text_normalization": "<string>",
  "apply_language_text_normalization": true,
  "pronunciation_dictionary_locators": [
    {
      "version_id": "<string>",
      "pronunciation_dictionary_id": "<string>"
    }
  ]
}
'

import requests

url = "https://api.highwayapi.ai/v3/elevenlabs-tts-flash-v2"

payload = {
    "seed": 123,
    "text": "<string>",
    "stream": True,
    "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": ["<string>"],
    "previous_request_ids": ["<string>"],
    "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>',
    stream: true,
    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: ['<string>'],
    previous_request_ids: ['<string>'],
    apply_text_normalization: '<string>',
    apply_language_text_normalization: true,
    pronunciation_dictionary_locators: [{version_id: '<string>', pronunciation_dictionary_id: '<string>'}]
  })
};

fetch('https://api.highwayapi.ai/v3/elevenlabs-tts-flash-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.highwayapi.ai/v3/elevenlabs-tts-flash-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>',
    'stream' => true,
    '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' => [
        '<string>'
    ],
    'previous_request_ids' => [
        '<string>'
    ],
    '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.highwayapi.ai/v3/elevenlabs-tts-flash-v2"

	payload := strings.NewReader("{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"stream\": true,\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    \"<string>\"\n  ],\n  \"previous_request_ids\": [\n    \"<string>\"\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.highwayapi.ai/v3/elevenlabs-tts-flash-v2")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"seed\": 123,\n  \"text\": \"<string>\",\n  \"stream\": true,\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    \"<string>\"\n  ],\n  \"previous_request_ids\": [\n    \"<string>\"\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.highwayapi.ai/v3/elevenlabs-tts-flash-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  \"stream\": true,\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    \"<string>\"\n  ],\n  \"previous_request_ids\": [\n    \"<string>\"\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

Convert text into speech using the voice of your choice and return audio.

Request Headers

string

required

Enum value: application/json

string

required

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

Request Body

integer

If specified, the system will try to sample deterministically. Repeated requests with the same seed and parameters should return the same result, but full determinism is not guaranteed.Value range: [0, 4294967295]

string

required

The text to convert into speech.

boolean

Whether to enable Stream mode.

string

required

The voice ID to use.

string

Text after the current request text. Used to improve speech continuity when concatenating multiple generations.

string

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

string

default:"mp3_44100_128"

The output format of the generated audio. The format is codec_sample_rate_bitrate. A 192 kbps bitrate for MP3 requires a Creator account or higher, and a 44.1 kHz sample rate for PCM requires a Pro account or higher.Options: 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

string

Text before the current request text. Used to improve speech continuity when concatenating multiple generations.

boolean

default:false

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

object

Hide properties

number

default:1

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

number

default:0

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

number

Determines the stability of voice generation and the randomness between each generation. Lower values provide a broader emotional range, while higher values may make the voice sound monotonous.

number

Determines how closely the AI tries to replicate the original voice.

boolean

default:true

Enhances similarity to the original speaker. Requires a slightly higher compute load and increases latency.

string[]

List of request_id values for subsequent samples. Used to maintain speech continuity when regenerating samples. Up to 3 request_id values can be passed.Array length: 0 - 3

string[]

List of request_id values for samples generated before the current generation. Can be used to improve speech continuity. Up to 3 request_id values can be passed.Array length: 0 - 3

string

default:"auto"

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

boolean

default:false

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

object[]

List of pronunciation dictionary locators (id, version_id) to apply to the text. They take effect in order. Each request can have up to 3 locators.Array length: 0 - 3

Hide properties

string

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

string

required

The ID of the pronunciation dictionary.

Response Information

Generated audio file Format: binary

ElevenLabs Speech-to-Text V2

ElevenLabs Text to Speech Flash V2.5

API Basics

Large Language Models

Images

Video

Audio

ElevenLabs Text-to-Speech Flash V2

Request Headers

Request Body

Response Information

​Request Headers

​Request Body

​Response Information

Request Headers

Request Body

Response Information