Áudio
Chatterbox
Chatterbox — Resemble AI's open-source TTS family: expressive text-to-speech and voice cloning, multilingual V3, low-latency Turbo and tiny Nano models, MIT
★ 27,1 mil estrelasMIT
Ver o guia →// audio · OpenBMB/VoxCPM
VoxCPM
VoxCPM é um projeto de áudio de código aberto de OpenBMB (OpenBMB/VoxCPM no GitHub). Tem 38.415 estrelas no GitHub e 4.343 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 8 de outubro de 2026.
VoxCPM2: tokenizer-free TTS for multilingual speech, creative voice design and true-to-life cloning
★ 38,4 mil estrelas⑂ 4,3 mil forksApache-2.0atualizado out 2026
▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
// dados do projeto
Dados do projeto
- Repositório
- OpenBMB/VoxCPM
- Estrelas no GitHub
- 38.415
- Forks
- 4.343
- Licença
- Apache-2.0
- Última atualização no GitHub
- 8 de outubro de 2026
- Categoria
- Áudio
- Tipo de ficha
- Guia de instalação completo
- Site oficial
- Official site
// como funciona
Como funciona
- Clarify your goal
Decide what you want from VoxCPM and check the README and requirements to confirm it fits your setup and Python environment.
- Get the code
Clone the repository from GitHub (github.com/OpenBMB/VoxCPM) or use the documented install channel if you do not need the source.
- Install and configure
Follow the README quickstart to install dependencies and set any required configuration or credentials.
- Run your first task
Work through the README's first example end to end, then adapt it to your own project or data.
// recursos
Por que as pessoas gostam tanto
Tokenizer-free TTS
A tokenizer-free architecture for text-to-speech from OpenBMB.
Multilingual generation
Generates speech across many languages.
Voice design
Create new voices creatively from descriptions, per the project highlights.
Voice cloning
True-to-life voice cloning from reference audio.
Production serving
Documents production deployment via Nano-vLLM and vLLM-Omni, plus on-device llama.cpp-omni inference.
Python API and CLI
Usable through a Python API, a CLI and a web demo.
Advertisement
// execute você mesmo
Execute você mesmo
- Clone the repository
Start by getting the source and entering the project directory.
git clone https://github.com/OpenBMB/VoxCPM.git cd VoxCPM - Install VoxCPM
Install the Python package from PyPI.
pip install voxcpm - Generate speech
Use the Python API or CLI to synthesize your first utterance or clone a voice.
voxcpm # see README for the exact command — CLI Usage
// casos de uso
O que você pode criar
- Multilingual voiceover generation
- Designing a unique brand voice without a voice actor
- Cloning a consenting speaker's voice for content
- Serving TTS at production scale with vLLM
Advertisement
// perguntas frequentes
Perguntas frequentes
Who maintains VoxCPM?
It is maintained by OpenBMB and contributors on GitHub, where the repository github.com/OpenBMB/VoxCPM is the canonical home for code, issues and releases.
Is VoxCPM free to use?
Yes — it is open source under the Apache-2.0 license. Read the license in the repository for what is permitted, including any conditions on redistribution or commercial use.
Does it need a paid API key?
No. VoxCPM runs locally or on your own serving stack; no API key is required.
How does VoxCPM compare to alternatives?
Compared with Coqui TTS: VoxCPM is a modern tokenizer-free model with voice design and cloning built in, versus Coqui's toolkit of classic architectures.
How do I get started?
Clone github.com/OpenBMB/VoxCPM, follow the README quickstart to install it, and run the documented first example before adapting it to your own work.
// continue explorando
Ferramentas semelhantes
Áudio
MOSS-TTS
MOSS-TTS family: open text-to-speech models for voice cloning, dialogue, voice design, and real-time agents
★ 4,2 mil estrelasApache-2.0
Ver o guia →Áudio
kokoclone
Voice cloning inside Kokoro: natural multilingual speech, your voice.
★ 203 estrelasApache-2.0
Ver o guia →Áudio
T5Gemma-TTS
Multilingual TTS with voice cloning and duration control, on T5Gemma.
★ 312 estrelasMIT
Ver o guia →Áudio
MOSS-TTSD
Multilingual long-form dialogue speech with zero-shot voice cloning.
★ 1,4 mil estrelasApache-2.0
Ver o guia →Áudio
index-tts
IndexTTS: industrial-level, controllable zero-shot text-to-speech with voice cloning
★ 24,4 mil estrelasNOASSERTION
Ver o guia →// alternativas
Alternativas em Áudio
Os outros projetos de Áudio com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se VoxCPM 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 VoxCPM: continue explorando dos dois lados dele.
- Retrieval-based-Voice-Conversion-WebUI★ 38,6 mil
Easily train a good VC model with voice data <= 10 mins!
- OpenVoice★ 37,8 mil
Instant voice cloning from MIT and MyShell — clone a voice from a short reference clip
- bark★ 39,3 mil
Suno's text-prompted generative audio model: speech, music and sound effects from text prompts
- MockingBird★ 36,9 mil
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
- ChatTTS★ 39,9 mil
A generative speech model built for daily dialogue — natural, conversational text-to-speech
- Fish Speech★ 33,3 mil
Fish Speech — Fish Audio's expressive open text-to-speech and voice cloning: SOTA-quality TTS you can self-host, under the Fish Audio Community License (check terms)
Baixe o VoxCPM
Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.