Assembling...
Neural text-to-speech framework supporting FastPitch, RAD-TTS, and HiFi-GAN vocoder architectures. Enables training custom voices with as little as 30 minutes of studio-quality audio and supports multi-speaker synthesis.
Train custom voices from 30 minutes of studio audio
Full prosody and pitch control via FastPitch architecture
Integrated HiFi-GAN vocoder for high-fidelity waveform generation
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.
// NeMo TTS — Text-to-Speech
import { synthesize } from "@arkitekton/voice";
const audio = await synthesize({
model: "vm-nv-003",
vendor: "nvidia",
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();GPU-accelerated speech AI and conversational frameworks