samuel-vitorino/sopro

A lightweight text-to-speech model with zero-shot voice cloning

What it solves

Sopro is a lightweight, high-performance text-to-speech (TTS) system designed to provide high-quality voice cloning and speech synthesis without requiring massive computing power. It addresses the need for efficient, on-device synthesis that can run on laptop CPUs or directly in a web browser.

How it works

Sopro uses a 120M-parameter model family (specifically sopro-v2-turbo) that supports zero-shot voice cloning from a short reference audio clip (5-20 seconds). It can operate in two modes: an offline path for maximum quality and a streaming path for low-latency audio emission. The system supports English, European Portuguese, French, and German, and can be deployed via Python, a CLI, or as an ONNX runtime for browser-based execution.

Who it’s for

Developers and creators who need a fast, lightweight TTS engine that can run locally on consumer hardware or in the browser, and those who want to clone voices from small audio samples without needing a cloud-based API.

Highlights

  • Ultra-lightweight: Only 120M parameters, allowing it to run on laptop CPUs and in-browser.
  • Zero-shot cloning: Clones voices from just 5-20 seconds of reference audio.
  • Low latency: Achieves ~300ms time-to-first-audio on laptop CPUs when streaming.
  • Multilingual support: Works across English, European Portuguese, French, and German.
  • Browser-ready: Fully functional in-browser demo via ONNX runtime.

Related

  • Project
    kyutai-labs/pocket-tts

    Pocket TTS is a 100 M‑parameter, CPU‑only text‑to‑speech library that streams audio with ~200 ms latency, supports multiple languages and voice cloning, and offers a Python API, CLI, and local HTTP server. It can be installed via pip (or uv) and runs faster than real‑time on modest hardware, with community‑trained models and several alternative runtimes for browsers and embedded devices.

  • Project
    tronghieuit/v-tts

    A lightweight Vietnamese text-to-speech system featuring multi-speaker synthesis and zero-shot voice cloning that runs efficiently on CPU.

  • Project
    OpenMOSS/MOSS-TTS-Nano

    A multilingual, tiny speech generation model with 0.1B parameters designed for real-time, CPU-based inference and high-fidelity voice cloning.

  • Project
    RVC-Boss/GPT-SoVITS

    A powerful few-shot voice conversion and text-to-speech system that can clone a voice using as little as 5 seconds of audio samples.

  • Project
    Edge0-AI/Audio8_TTS

    A compact multilingual text-to-speech model with zero-shot voice cloning, available in 0.6B and 0.1B parameter versions for high-efficiency speech synthesis.