LibreAI / Áudio / FlashLabs-Chroma
// audio · FlashLabs-AI-Corp/FlashLabs-Chroma

FlashLabs-Chroma

FlashLabs-Chroma é um projeto de áudio de código aberto de FlashLabs-AI-Corp (FlashLabs-AI-Corp/FlashLabs-Chroma no GitHub). Tem 549 estrelas no GitHub e 57 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 4 de setembro de 2026.

Open-source real-time spoken dialogue with personalized voice cloning.

💎 Joia escondida★ 549 estrelas⑂ 57 forksApache-2.0atualizado set 2026
▦ 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

Estrelas no GitHub
549
Forks
57
Licença
Apache-2.0
Última atualização no GitHub
4 de setembro de 2026
Categoria
Áudio
Tipo de ficha
Joia escondida: uma página mais breve para um projeto menos conhecido
Site oficial
Official site
// como funciona

Como funciona

  1. Clone and explore

    Open the notebooks to see the model in action.

  2. Load the model

    Download weights and the dialogue pipeline.

  3. Clone a voice

    Provide a sample for a personalized speaking voice.

  4. Talk in real time

    Hold a live spoken conversation with the model.

// recursos

Por que as pessoas gostam tanto

End-to-end dialogue

One model handles the full speech-to-speech loop.

Real-time

Designed for live, low-latency conversation.

Personalized cloning

Speaks in a cloned voice unique to you.

Zero-shot voice

Clones from a sample without lengthy training.

Notebook workflow

Experiment-friendly Jupyter-based code.

Apache-2.0 license

Commercial-friendly open-source terms.

Advertisement
// execute você mesmo

Execute você mesmo

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma.git
    cd FlashLabs-Chroma
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project's launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// casos de uso

O que você pode criar

  • Prototype a real-time voice agent.
  • Research end-to-end spoken dialogue.
  • Build a personalized voice companion.
  • Demo open-source voice AI live.
Advertisement
// perguntas frequentes

Perguntas frequentes

Who maintains FlashLabs-Chroma?

It is an open-source project at FlashLabs-AI-Corp/FlashLabs-Chroma with 57 forks. Check the repo's contributors and recent commits to see how active maintenance is.

Is FlashLabs-Chroma free for commercial use?

Apache 2.0 licensed — commercial use allowed with attribution.

What does end-to-end mean here?

A single model goes from spoken input to spoken output, without separate STT and TTS stages.

How much compute do I need?

Real-time speech models generally want a GPU — check the notebooks for guidance.

Can it clone my voice?

Yes — personalized and zero-shot voice cloning are headline features.

// continue explorando

Ferramentas semelhantes

Áudio

dia

A TTS model capable of generating ultra-realistic dialogue in one pass.

★ 19,4 mil estrelasApache-2.0
Ver o guia →
Áudio

F5 TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

★ 15,3 mil estrelasMIT
Ver o guia →
Áudio

EmotiVoice

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

★ 8,5 mil estrelasApache-2.0
Ver o guia →
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

Real-Time-Voice-Cloning

Clone a voice from 5 seconds of audio and generate arbitrary speech in real time

★ 60,2 mil estrelasNOASSERTION
Ver o guia →
Áudio

VieNeu-TTS

Vietnamese TTS with instant voice cloning — on-device, real-time CPU inference, 48 kHz audio

★ 2,8 mil estrelasApache-2.0
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 FlashLabs-Chroma 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 FlashLabs-Chroma: continue explorando dos dois lados dele.

  • joinly★ 566

    Give AI agents a seat in your meetings.

  • talk-to-fengge★ 469

    Clone anyone's voice and personality for real-time conversation.

  • opentypeless★ 582

    Open-source AI voice typing: hotkey, speak, get polished text anywhere.

  • TeroSubtitler★ 467

    Free, cross-platform subtitle editor with AI transcription tools.

  • pindrop★ 628

    A macOS menu-bar dictation app powered by local WhisperKit.

  • ChatTTS-OpenVoice★ 466

    Fuse ChatTTS with OpenVoice: clone a voice from a 10-second clip.

Baixe o FlashLabs-Chroma

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