ElevenLabs texto a voz Flash V2.5

curl --request POST \
  --url https://api.highwayapi.ai/v3/elevenlabs-tts-flash-v2.5 \
  --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-v2.5"

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-v2.5', 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-v2.5",
  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-v2.5"

	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-v2.5")
  .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-v2.5")

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-v2.5

ElevenLabs texto a voz Flash V2.5

curl --request POST \
  --url https://api.highwayapi.ai/v3/elevenlabs-tts-flash-v2.5 \
  --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-v2.5"

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-v2.5', 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-v2.5",
  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-v2.5"

	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-v2.5")
  .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-v2.5")

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

Convierte texto a voz con la voz que elijas y devuelve el audio.

Encabezados de la solicitud

string

requerido

Valores enumerados: application/json

string

requerido

Formato de autenticación Bearer: Bearer {{API Key}}.

Cuerpo de la solicitud

integer

Si se especifica, el sistema intentará muestrear de forma determinista. Las solicitudes repetidas con el mismo seed y los mismos parámetros deberían devolver el mismo resultado, pero no se garantiza una determinación completa.Rango de valores: [0, 4294967295]

string

requerido

El texto que se convertirá a voz.

boolean

Si se activa el modo Stream

string

requerido

El ID de la voz que se utilizará.

string

El texto posterior al texto de la solicitud actual. Se utiliza para mejorar la continuidad de la voz al unir múltiples generaciones.

string

Código de idioma (ISO 639-1) utilizado para el modelo y la normalización del texto. Si el modelo no admite este código de idioma, se devolverá un error.

string

predeterminado:"mp3_44100_128"

Formato de salida del audio generado. El formato es codec_sample_rate_bitrate. La tasa de bits de 192 kbps para MP3 requiere una cuenta Creator o superior; la frecuencia de muestreo de 44.1 kHz para PCM requiere una cuenta Pro o superior.Valores opcionales: 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

El texto anterior al texto de la solicitud actual. Se utiliza para mejorar la continuidad de la voz al unir múltiples generaciones.

boolean

predeterminado:false

Si es true, se usa la versión IVC de la voz en lugar de la versión PVC. Esta es una solución temporal para la mayor latencia de la versión PVC.

object

Ocultar propiedades

number

predeterminado:1

Ajusta la velocidad de la voz. 1.0 es la velocidad predeterminada; un valor inferior a 1.0 ralentiza el habla, y un valor superior a 1.0 la acelera.

number

predeterminado:0

Determina el grado de exageración del estilo de la voz. Intenta amplificar el estilo del hablante original. Establecerlo en un valor distinto de 0 consumirá más recursos de cómputo y puede aumentar la latencia.

number

Determina la estabilidad de la generación de voz y la aleatoriedad entre cada generación. Los valores más bajos aportan un rango emocional más amplio; los valores más altos pueden hacer que la voz suene monótona.

number

Determina qué tanto se ajusta la IA al intentar replicar la voz original.

boolean

predeterminado:true

Mejora la similitud con el hablante original. Requiere una carga de cómputo ligeramente mayor y aumentará la latencia.

string[]

Lista de request_id de muestras posteriores. Se utiliza para mantener la continuidad de la voz al regenerar muestras. Se pueden enviar como máximo 3 request_id.Longitud del arreglo: 0 - 3

string[]

Lista de request_id de muestras generadas antes de la generación actual. Puede utilizarse para mejorar la continuidad de la voz. Se pueden enviar como máximo 3 request_id.Longitud del arreglo: 0 - 3

string

predeterminado:"auto"

Controla la normalización del texto. ‘auto’ deja que el sistema decida, ‘on’ siempre normaliza y ‘off’ la omite.Valores opcionales: auto, on, off

boolean

predeterminado:false

Controla la normalización lingüística del texto para ciertos idiomas compatibles con el fin de lograr una pronunciación más natural. Advertencia: puede aumentar significativamente la latencia. Actualmente solo se admite japonés.

object[]

Lista de localizadores de diccionarios de pronunciación (id, version_id) que deben aplicarse al texto. Se aplican en orden. Cada solicitud puede tener como máximo 3 localizadores.Longitud del arreglo: 0 - 3

Ocultar propiedades

string

El ID de la versión del diccionario de pronunciación. Si no se especifica, se utiliza la versión más reciente.

string

requerido

El ID del diccionario de pronunciación.

Información de respuesta

Archivo de audio generado Formato: binary

Conceptos básicos de API

Modelos de lenguaje

Imágenes

Vídeo

Audio

ElevenLabs texto a voz Flash V2.5

Encabezados de la solicitud

Cuerpo de la solicitud

Información de respuesta

​Encabezados de la solicitud

​Cuerpo de la solicitud

​Información de respuesta

Encabezados de la solicitud

Cuerpo de la solicitud

Información de respuesta