Synthèse vocale ElevenLabs 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

Synthèse vocale ElevenLabs 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

Convertissez du texte en parole avec la voix de votre choix et renvoie l’audio.

En-têtes de requête

string

requis

Valeurs d’énumération : application/json

string

requis

Format d’authentification Bearer : Bearer {{API Key}}.

Corps de la requête

integer

Si spécifié, le système essaiera d’échantillonner de manière déterministe. Les requêtes répétées avec le même seed et les mêmes paramètres devraient renvoyer le même résultat, mais le déterminisme total n’est pas garanti.Plage de valeurs : [0, 4294967295]

string

requis

Le texte à convertir en parole.

boolean

Indique s’il faut activer le mode Stream

string

requis

L’ID de la voix à utiliser.

string

Le texte qui suit le texte de la requête actuelle. Utilisé pour améliorer la cohérence de la voix lors de la concaténation de plusieurs générations.

string

Code de langue (ISO 639-1) utilisé pour le modèle et la normalisation du texte. Si le modèle ne prend pas en charge ce code de langue, une erreur sera renvoyée.

string

défaut:"mp3_44100_128"

Format de sortie de l’audio généré. Le format est codec_sample_rate_bitrate. Le débit MP3 de 192 kbps nécessite un compte Creator ou supérieur, et la fréquence d’échantillonnage PCM de 44,1 kHz nécessite un compte Pro ou supérieur.Valeurs possibles : 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

Le texte qui précède le texte de la requête actuelle. Utilisé pour améliorer la cohérence de la voix lors de la concaténation de plusieurs générations.

boolean

défaut:false

Si true, utilise la version IVC de la voix au lieu de la version PVC. Il s’agit d’une solution temporaire pour la latence élevée de la version PVC.

object

Masquer properties

number

défaut:1

Ajuste la vitesse de la voix. 1.0 est la vitesse par défaut ; une valeur inférieure à 1.0 ralentit le débit, tandis qu’une valeur supérieure à 1.0 l’accélère.

number

défaut:0

Détermine le degré d’exagération du style vocal. Tente d’amplifier le style du locuteur d’origine. Une valeur différente de 0 consomme davantage de ressources de calcul et peut augmenter la latence.

number

Détermine la stabilité de la génération vocale et le niveau d’aléatoire entre chaque génération. Des valeurs plus faibles offrent une plage émotionnelle plus large, tandis que des valeurs plus élevées peuvent rendre la voix monotone.

number

Détermine dans quelle mesure l’IA tente de reproduire fidèlement la voix d’origine.

boolean

défaut:true

Renforce la similarité avec le locuteur d’origine. Nécessite une charge de calcul légèrement plus élevée et augmente la latence.

string[]

Liste des request_id des échantillons suivants. Utilisée pour maintenir la cohérence de la voix lors de la régénération d’échantillons. Jusqu’à 3 request_id peuvent être transmis.Longueur du tableau : 0 - 3

string[]

Liste des request_id des échantillons déjà générés avant la génération actuelle. Peut être utilisée pour améliorer la cohérence de la voix. Jusqu’à 3 request_id peuvent être transmis.Longueur du tableau : 0 - 3

string

défaut:"auto"

Contrôle la normalisation du texte. ‘auto’ laisse le système décider, ‘on’ normalise toujours, et ‘off’ l’ignore.Valeurs possibles : auto, on, off

boolean

défaut:false

Contrôle la normalisation linguistique du texte pour certaines langues prises en charge afin d’obtenir une prononciation plus naturelle. Avertissement : cela peut augmenter considérablement la latence. Actuellement, seul le japonais est pris en charge.

object[]

Liste des localisateurs de dictionnaire de prononciation (id, version_id) à appliquer au texte. Ils prennent effet dans l’ordre. Chaque requête peut contenir jusqu’à 3 localisateurs.Longueur du tableau : 0 - 3

Masquer properties

string

ID de la version du dictionnaire de prononciation. Si non spécifié, la dernière version est utilisée.

string

requis

ID du dictionnaire de prononciation.

Informations de réponse

Fichier audio généré Format : binary

ElevenLabs parole en texte V2

ElevenLabs synthèse vocale Flash V2.5

Bases de l'API

Grands modèles de langage

Images

Vidéo

Audio

Synthèse vocale ElevenLabs Flash V2

En-têtes de requête

Corps de la requête

Informations de réponse

​En-têtes de requête

​Corps de la requête

​Informations de réponse

En-têtes de requête

Corps de la requête

Informations de réponse