// audio · myshell-ai/MeloTTS

MeloTTS

MeloTTS é um projeto de áudio de código aberto de myshell-ai (myshell-ai/MeloTTS no GitHub). Tem 7.661 estrelas no GitHub e 1.079 forks, é publicado sob a licença MIT e foi atualizado pela última vez no GitHub em 24 de dezembro de 2024.

MeloTTS — multilingual text-to-speech for English, Spanish, French, Chinese, Japanese and Korean.

★ 7,7 mil estrelas⑂ 1,1 mil forksMITatualizado dez 2024

Ver no GitHub ↗

▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.

// dados do projeto

Dados do projeto

Repositório: myshell-ai/MeloTTS
Estrelas no GitHub: 7.661
Forks: 1.079
Licença: MIT
Última atualização no GitHub: 24 de dezembro de 2024
Categoria: Áudio
Tipo de ficha: Guia de instalação completo

// como funciona

Como funciona

Clarify your goal
Pick the language (or languages) you need voices for, and whether you will call the library from Python, the CLI or the Web UI.
Get the project
Clone myshell-ai/MeloTTS from GitHub (or use the install path in the run steps below) and skim its README for the parts relevant to your goal.
Install and configure
Clone the repo and install it following the README's usage instructions for your chosen language models.
Run your first task
Synthesise a short sentence in one language on CPU, check the audio quality and speed, then try a second language or a mixed Chinese-English line.

// recursos

Por que as pessoas gostam tanto

Six languages

Speakers for English, Spanish, French, Chinese, Japanese and Korean in one library.

Mixed Chinese and English

The Chinese speaker supports mixed Chinese and English text, a common pain point for bilingual content.

CPU real-time inference

Fast enough to synthesise in real time on CPU, so voice features do not require a GPU.

Web UI and CLI

Beyond the Python library, a contributed Web UI and command-line interface make quick tests easy.

High-quality voices

Positioned as a high-quality TTS library rather than a tiny embedded synthesizer, based on MyShell's research.

Open MIT library

Free to embed in your own applications under the MIT license.

// execute você mesmo

Execute você mesmo

Clone the repository
Get the source from the official GitHub repository for MeloTTS.
```
git clone https://github.com/myshell-ai/MeloTTS.git
cd MeloTTS
```
Install MeloTTS
Clone the repository and install following the README's usage section for your platform and language.
```
git clone https://github.com/myshell-ai/MeloTTS.git
cd MeloTTS  # then follow the README install/usage steps
```
Synthesise speech
Use the Python API, CLI or Web UI from the README to generate speech in your chosen language.
```
# Follow the README usage examples to synthesise your first sentence — see README
```

// casos de uso

O que você pode criar

Adding multilingual voice output to a language-learning app
Generating narration for videos in Spanish, Japanese or Korean from one library
Giving a local assistant a voice that runs on CPU without cloud calls
Reading mixed Chinese-English study material aloud naturally

// perguntas frequentes

Perguntas frequentes

Who maintains MeloTTS?

myshell-ai (MyShell.ai), through the myshell-ai/MeloTTS repository.

Is MeloTTS free to use?

Yes — the project is open source under the MIT license as recorded for this listing. You can use, modify and distribute it under the MIT terms.

Does MeloTTS need a paid API key?

No API key is needed — synthesis runs locally, including on CPU; MeloTTS is free under the MIT license.

How does MeloTTS compare to a cloud TTS service?

Cloud TTS charges per character and needs connectivity, but offers many managed voices. MeloTTS runs locally in six languages at CPU real-time speed for free — fewer knobs, but private, offline and embeddable.

How do I get started with MeloTTS?

Os outros projetos de Áudio com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se MeloTTS não for o ideal para você.

MoneyPrinterTurbo★ 128,3 mil
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
Whisper★ 109,9 mil
Robust Speech Recognition via Large-Scale Weak Supervision
GPT-SoVITS★ 62,3 mil
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Real-Time-Voice-Cloning★ 60,2 mil
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
whisper.cpp★ 54,1 mil
Port of OpenAI's Whisper model in C/C++

// mais em audio

Mais em Áudio

Projetos de Áudio próximos no catálogo, os mais próximos em estrelas de MeloTTS: continue explorando dos dois lados dele.

vits★ 7,9 mil
VITS — the original end-to-end text-to-speech model: a conditional VAE with adversarial learning, in PyTorch.
ODS★ 7,0 mil
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
EmotiVoice★ 8,5 mil
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
espeak-ng★ 6,9 mil
eSpeak NG — the compact open-source speech synthesizer for 100+ languages, small enough to embed anywhere.
librosa★ 8,6 mil
Python library for audio and music analysis
argmax-oss-swift★ 6,4 mil
On-device Speech AI for Apple Silicon

Baixe o MeloTTS

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.

Ver no GitHub ↗← Mais ferramentas de Áudio