Tasks

Text-to-Speech

Text-to-Speech (TTS) is the task of generating natural sounding speech given text input. TTS models can be extended to have a single model that generates speech for multiple speakers and multiple languages.

Inputs
Input

I love audio models on the Hub!

Text-to-Speech Model
Output

About Text-to-Speech

Use Cases

Text-to-Speech (TTS) models can be used in any speech-enabled application that requires converting text to speech imitating human voice.

Voice Assistants

TTS models are used to create voice assistants on smart devices. These models are a better alternative compared to concatenative methods where the assistant is built by recording sounds and mapping them, since the outputs in TTS models contain elements in natural speech such as emphasis.

Announcement Systems

TTS models are widely used in airport and public transportation announcement systems to convert the announcement of a given text into speech.

Inference Endpoints

The Hub contains over 1500 TTS models that you can use right away by trying out the widgets directly in the browser or calling the models as a service using Inference Endpoints. Here is a simple code snippet to get you started:

import json
import requests

headers = {"Authorization": f"Bearer {API_TOKEN}"}
API_URL = "https://api-inference.huggingface.co/models/microsoft/speecht5_tts"

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response

output = query({"text_inputs": "Max is the best doggo."})

You can also use libraries such as espnet or transformers if you want to handle the Inference directly.

Direct Inference

Now, you can also use the Text-to-Speech pipeline in Transformers to synthesise high quality voice.

from transformers import pipeline

synthesizer = pipeline("text-to-speech", "suno/bark")

synthesizer("Look I am generating speech in three lines of code!")

You can use huggingface.js to infer summarization models on Hugging Face Hub.

import { HfInference } from "@huggingface/inference";

const inference = new HfInference(HF_TOKEN);
await inference.textToSpeech({
    model: "facebook/mms-tts",
    inputs: "text to generate speech from",
});

Useful Resources

Compatible libraries

Text-to-Speech demo
Models for Text-to-Speech
Browse Models (1,913)
Datasets for Text-to-Speech
Browse Datasets (159)

Note Thousands of short audio clips of a single speaker.

Spaces using Text-to-Speech

Note An application for generate highly realistic, multilingual speech.

Note XTTS is a Voice generation model that lets you clone voices into different languages.

Note An application that synthesizes speech for various speaker types.

Metrics for Text-to-Speech
mel cepstral distortion
The Mel Cepstral Distortion (MCD) metric is used to calculate the quality of generated speech.