Hecho para agentes de voz que no pueden esperar 600ms
Regístrate gratisIniciar sesión

ElevenLabs: Eleven Multilingual v2

elevenlabs/eleven-multilingual-v2
activo tts 1 proveedor
Playground

ElevenLabs' most life-like, emotionally rich model in 29 languages, best for voice overs, audiobooks, post-production and other content creation.

AutorElevenLabs
Idiomas29 idiomas
VocesCargando...
Formatos de respuestaSíncrono: MP3 · WAV · PCM · Opus · µ-law · A-law
Streaming: MP3 · PCM · Opus · µ-law · A-law
Estadoactivo

Proveedores

Distintos proveedores pueden alojar el mismo modelo. Elige un proveedor cuando necesites un backend fijo, o deja que el enrutamiento elija entre ellos.

ProveedorSlugPor 1k caracteresLatenciaiEn TTS, la latencia se mide como el tiempo hasta el primer byte de audio. En STT, se mide como el tiempo hasta el primer token.ModosDisponibilidad
ElevenLabs 14 parámetros
elevenlabs
$0,1
—
Síncrono · Streaming

Idiomas admitidos

29 idiomas
English en
Japanese ja
Chinese zh
German de
Hindi hi
French fr
Korean ko
Portuguese pt
Italian it
Spanish es
Indonesian id
Dutch nl
Turkish tr
Filipino fil
Polish pl
Swedish sv
Bulgarian bg
Romanian ro
Arabic ar
Czech cs
Greek el
Finnish fi
Croatian hr
Malay ms
Slovak sk
Danish da
Tamil ta
Ukrainian uk
Russian ru

Voces

Funciones

Text to speech

Generates spoken audio from text input.

text_to_speech
Streaming

Streams synthesized audio incrementally over a persistent connection (WebSocket/SSE).

streaming
Synchronous

Synthesizes speech from fully-submitted text in a single synchronous request.

synchronous
Multilingual

Supports 29 languages.

multilingual
Expressive speech

Designed for expressive, natural, or emotionally rich generated speech.

expressive_speech
Fine-tuning

Supports provider-managed fine-tuning for this model.

fine_tuning
Style control

Supports explicit style control for generated or converted speech.

style_control
Speaker boost

Supports speaker boost voice enhancement controls.

speaker_boost

Código

Cliente
Modo
Lenguaje

TTS en streaming con el ElevenLabs SDK

Enruta el ElevenLabs SDK a través de AllModels y transmite la respuesta de audio.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "elevenlabs/eleven-multilingual-v2",
  outputFormat: "mp3_44100_128"
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}