Assembling...
Controllable text-to-speech model trained and released by Hugging Face. Generates speech conditioned on natural language descriptions of the desired voice characteristics, enabling prompt-based voice control without fine-tuning.
Control voice with natural language descriptions like 'a calm female narrator'
Open training recipes enable reproduction and customization
Integrates natively with the Hugging Face Transformers 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.
// Parler-TTS — Text-to-Speech
import { synthesize } from "@arkitekton/voice";
const audio = await synthesize({
model: "vm-hf-003",
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