Assembling...
Flagship text-to-speech model with 800+ pre-built voices spanning 142 languages and accents. Features instant voice cloning, fine-grained emotion control, SSML support, and streaming output with low latency.
800+ pre-built voices covering 142 languages and regional accents
Instant voice cloning from minimal reference audio
Fine-grained emotion and style controls via API parameters
Generate natural-sounding narration for long-form content with consistent voice quality.
Deliver voice alerts and notifications with expressive, human-like speech synthesis.
Produce audio content in multiple languages from a single text source.
Power low-latency voice responses in interactive applications and games.
// Play3.0 — Text-to-Speech
import { synthesize } from "@arkitekton/voice";
const audio = await synthesize({
model: "vm-ph-002",
vendor: "playht",
input: "Hello, welcome to Arkitekton.",
voice: "alloy",
response_format: "mp3",
speed: 1.0,
});
// Play the audio
const blob = new Blob([audio], { type: "audio/mp3" });
const url = URL.createObjectURL(blob);
const player = new Audio(url);
player.play();Conversational TTS with massive voice and language coverage