Helpingai TTS V1

🚀 HelpingAI-TTS-v1 🎤🔥

Welcome to HelpingAI-TTS-v1, a cutting-edge Text-to-Speech (TTS) solution that offers personalization, great vibes, and crystal - clear audio. Whether you need your text to sound cheerful, emotional, or like a friendly chat, this model has you covered. 💯

🚀 Quick Start

HelpingAI-TTS-v1 is designed to generate high - quality, customizable speech. It can understand the context of your text and bring it to life with style. You can customize aspects such as speech speed, tone (cheerful or serious), and get the perfect audio output. 🎧

✨ Features

• Expressive Speech: This TTS allows you to describe the tone, speed, and vibe of the speech. Whether it's a peppy greeting or a chill conversation, the model can handle it.
• Top - Notch Quality: It produces super clean audio with no static, just pure, high - quality sound.
• Highly Customizable: You can play with emotions, tone, and accents to make the speech truly personal. 🌍

📦 Installation

Ready to start? Here's how to set up HelpingAI-TTS-v1 in seconds:

pip install git+https://github.com/huggingface/parler-tts.git

💻 Usage Examples

Basic Usage

Here's the code to use HelpingAI-TTS-v1. It's very simple: just input your text and describe how you want it to sound.

import torch
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf

# Choose your device (GPU or CPU)
device = "cuda:0" if torch.cuda.is_available() else "cpu"

# Load the model and tokenizers
model = ParlerTTSForConditionalGeneration.from_pretrained("HelpingAI/HelpingAI-TTS-v1").to(device)
tokenizer = AutoTokenizer.from_pretrained("HelpingAI/HelpingAI-TTS-v1")
description_tokenizer = AutoTokenizer.from_pretrained(model.config.text_encoder._name_or_path)

# Customize your inputs: text + description
prompt = "Hey, what's up? How’s it going?"
description = "A friendly, upbeat, and casual tone with a moderate speed. Speaker sounds confident and relaxed."

# Tokenize the inputs
input_ids = description_tokenizer(description, return_tensors="pt").input_ids.to(device)
prompt_input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)

# Generate the audio
generation = model.generate(input_ids=input_ids, prompt_input_ids=prompt_input_ids)
audio_arr = generation.cpu().numpy().squeeze()

# Save the audio to a file
sf.write("output.wav", audio_arr, model.config.sampling_rate)

This code will generate a super clean .wav file with the desired speech. 🔥

📚 Documentation

How It Works

1. Transcript: The text you want to convert to speech. It can be in any style, casual or formal.
2. Caption: Describes the desired sound of the speech. You can specify a fast - paced, exciting vibe or a calm, soothing tone. 🔥

Language Support

HelpingAI-TTS-v1 officially supports over 20 languages and has unofficial support for a few more, offering global accessibility. 🌏

• Assamese
• Bengali
• Bodo
• Dogri
• Kannada
• Malayalam
• Marathi
• Sanskrit
• Nepali
• English
• Telugu
• Hindi
• Gujarati
• Konkani
• Maithili
• Manipuri
• Odia
• Santali
• Sindhi
• Tamil
• Urdu
• Chhattisgarhi
• Kashmiri
• Punjabi

📄 License

This project is licensed under the apache - 2.0 license.

Powered by HelpingAI, where we blend emotional intelligence with tech. 🌟