Assembling...
Fully generative text-to-audio model capable of producing speech, music, background noise, and non-verbal sounds like laughter, sighing, and crying. Uses a GPT-style transformer architecture for unconditioned audio generation.
Generates laughter, sighing, crying, and other non-verbal sounds naturally
Fully generative model creates speech, music, and ambient audio
MIT license with active community and prompt engineering ecosystem
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.
// Bark (Suno) — Text-to-Speech
import { synthesize } from "@arkitekton/voice";
const audio = await synthesize({
model: "vm-hf-001",
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