Assembling...
Real-time voice cloning model that reproduces a target speaker's voice from a short reference clip. Supports 17 languages, streaming synthesis, and fine-tuning on custom datasets with the Coqui TTS training framework.
Clone any voice from a 6-second reference clip in real time
17-language multilingual support with cross-lingual voice transfer
MPL 2.0 license with active fine-tuning and training community
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.
// XTTS v2 (Coqui) — Text-to-Speech
import { synthesize } from "@arkitekton/voice";
const audio = await synthesize({
model: "vm-hf-005",
vendor: "huggingface",
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();Community-driven open-source speech models and toolkits