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

Konvertiert Text mit der von Ihnen gewählten Stimme in Sprache und gibt Audio zurück.

Anfrageheader

string

erforderlich

Enumerationswert: application/json

string

erforderlich

Bearer-Authentifizierungsformat: Bearer {{API-Schlüssel}}.

Anfragetext

integer

Falls angegeben, versucht das System, so deterministisch wie möglich zu sampeln. Wiederholte Anfragen mit demselben seed und denselben Parametern sollten dasselbe Ergebnis zurückgeben, eine vollständige Deterministik wird jedoch nicht garantiert.Wertebereich: [0, 4294967295]

string

erforderlich

Der Text, der in Sprache konvertiert werden soll.

boolean

Ob der Stream-Modus aktiviert werden soll.

string

erforderlich

Die zu verwendende Sprach-ID.

string

Der Text nach dem Text der aktuellen Anfrage. Wird verwendet, um die Sprachkohärenz beim Zusammenfügen mehrerer Generierungen zu verbessern.

string

Sprachcode (ISO 639-1), der für das Modell und die Textnormalisierung verwendet wird. Wenn das Modell diesen Sprachcode nicht unterstützt, wird ein Fehler zurückgegeben.

string

Standard:"mp3_44100_128"

Ausgabeformat des generierten Audios. Das Format lautet codec_sample_rate_bitrate. Eine Bitrate von 192 kbps für MP3 erfordert ein Creator-Konto oder höher; eine Abtastrate von 44,1 kHz für PCM erfordert ein Pro-Konto oder höher.Optionale Werte: 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

Der Text vor dem Text der aktuellen Anfrage. Wird verwendet, um die Sprachkohärenz beim Zusammenfügen mehrerer Generierungen zu verbessern.

boolean

Standard:false

Wenn true, wird die IVC-Version der Stimme anstelle der PVC-Version verwendet. Dies ist eine temporäre Lösung für die höhere Latenz der PVC-Version.

object

Ausblenden properties

number

Standard:1

Passt die Geschwindigkeit der Stimme an. 1.0 ist die Standardgeschwindigkeit; Werte kleiner als 1.0 verlangsamen das Sprechtempo, Werte größer als 1.0 beschleunigen es.

number

Standard:0

Bestimmt, wie stark der Sprachstil überzeichnet wird. Versucht, den Stil des ursprünglichen Sprechers zu verstärken. Bei einem Wert ungleich 0 werden mehr Rechenressourcen verbraucht und die Latenz kann steigen.

number

Bestimmt die Stabilität der Sprachgenerierung und die Zufälligkeit zwischen einzelnen Generierungen. Niedrigere Werte sorgen für eine größere emotionale Bandbreite, höhere Werte können zu monotoner Sprache führen.

number

Bestimmt, wie eng sich die KI beim Versuch, die ursprüngliche Stimme nachzubilden, an diese annähert.

boolean

Standard:true

Erhöht die Ähnlichkeit mit dem ursprünglichen Sprecher. Benötigt etwas mehr Rechenleistung und erhöht die Latenz.

string[]

Liste der request_id nachfolgender Samples. Wird verwendet, um die Sprachkohärenz beim erneuten Generieren von Samples beizubehalten. Es können maximal 3 request_id übergeben werden.Array-Länge: 0 - 3

string[]

Liste der request_id von Samples, die vor der aktuellen Generierung bereits generiert wurden. Kann verwendet werden, um die Sprachkohärenz zu verbessern. Es können maximal 3 request_id übergeben werden.Array-Länge: 0 - 3

string

Standard:"auto"

Steuert die Textnormalisierung. ‘auto’ wird vom System entschieden, ‘on’ normalisiert immer, ‘off’ überspringt sie.Optionale Werte: auto, on, off

boolean

Standard:false

Steuert die sprachspezifische Textnormalisierung für bestimmte unterstützte Sprachen, um eine natürlichere Aussprache zu erzielen. Warnung: Dies kann die Latenz deutlich erhöhen. Derzeit wird nur Japanisch unterstützt.

object[]

Liste der Aussprachewörterbuch-Locators (id, version_id), die auf den Text angewendet werden sollen. Sie werden der Reihe nach angewendet. Pro Anfrage sind maximal 3 Locators möglich.Array-Länge: 0 - 3

Ausblenden properties

string

Die ID der Version des Aussprachewörterbuchs. Wenn nicht angegeben, wird die neueste Version verwendet.

string

erforderlich

Die ID des Aussprachewörterbuchs.

Antwortinformationen

Generierte Audiodatei Format: binary

ElevenLabs Sprache-zu-Text V2

Zurück

ElevenLabs Text-to-Speech Flash V2.5

Weiter

API-Grundlagen

Große Sprachmodelle

Bilder

Video

Audio

ElevenLabs Text-to-Speech Flash V2

Anfrageheader

Anfragetext

Antwortinformationen

​Anfrageheader

​Anfragetext

​Antwortinformationen

Anfrageheader

Anfragetext

Antwortinformationen