Cette page est affichée en anglais. Une traduction française est en cours.
ScriptsApr 1, 2026·1 min de lecture

Zonos — Multilingual TTS with Voice Cloning

Zonos is an open-weight TTS model trained on 200K+ hours of speech. 7.2K+ stars. Voice cloning, 5 languages, emotion control. Apache 2.0.

assetLangBanner.body
Introduction

Zonos is a leading open-weight text-to-speech model trained on more than 200,000 hours of varied multilingual speech. With 7,200+ GitHub stars and Apache 2.0 license, it generates natural speech from text with zero-shot voice cloning from brief speaker samples, supports English, Japanese, Chinese, French, and German, provides fine-grained control over speaking rate, pitch, emotion, and audio quality, achieves ~2x real-time factor on RTX 4090, and includes Gradio web interface and Docker support.

Best for: Developers building multilingual voice applications with voice cloning Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf


Key Features

  • 200K+ hours training data
  • Zero-shot voice cloning
  • 5 languages (EN, JA, ZH, FR, DE)
  • Rate, pitch, emotion, quality control
  • ~2x realtime on RTX 4090
  • Gradio UI and Docker

FAQ

Q: What is Zonos? A: Open-weight TTS with 7.2K+ stars. 200K+ hours training, voice cloning, 5 languages, emotion control. Apache 2.0.

Q: How do I install Zonos? A: Clone repo, pip install -e . Requires Linux/macOS with 6GB+ GPU.


🙏

Source et remerciements

Zyphra/Zonos — 7,200+ GitHub stars

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires