Cartesia: Sonic 3.6
Cartesia's most lifelike text-to-speech model (recommended), #1 on the Artificial Analysis Speech Arena leaderboards, with sub-90ms latency and native support for 44 languages.
Streaming: PCM · µ-law · A-law
Modelos variantes
Son IDs de modelo nativos que el autor o proveedor acepta para la misma familia de modelos canónica.
Proveedores
Distintos proveedores pueden alojar el mismo modelo. Elige un proveedor cuando necesites un backend fijo, o deja que el enrutamiento elija entre ellos.
Idiomas admitidos
en
fr
de
es
pt
zh
ja
hi
it
ko
nl
pl
ru
sv
tr
tl
bg
ro
ar
cs
el
fi
hr
ms
sk
da
ta
uk
hu
no
vi
bn
th
he
ka
id
te
gu
kn
ml
mr
pa
or
ur
Voces
Funciones
Generates spoken audio from text input.
text_to_speech
Low-latency streaming TTS over WebSocket; raw PCM output (pcm_f32le/pcm_s16le/pcm_mulaw/pcm_alaw).
streaming
Synthesizes speech from fully-submitted text in a single synchronous request.
synchronous
Supports 44 languages (adds Odia and Urdu over Sonic 3.5).
multilingual
Supports instant and professional voice clones.
voice_cloning
Speed (0.6-1.5, default 1.0), volume (0.5-2.0, default 1.0) and emotion control (neutral/calm/angry/content/sad/scared; emotion guidance is English-only).
speed_emotion_control
Código
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: "cartesia/sonic-3-6",
outputFormat: "mp3_44100_128"
}, {
queryParams: {
provider: {
"only": [
"cartesia"
]
}
}
});
const reader = stream.getReader();
for (;;) {
const { done, value } = await reader.read();
if (done) break;
// Write value to your response, file, or audio playback pipeline.
}