Chatterbox: State-of-the-Art Open-Source Text-to-Speech (TTS) Model

Chatterbox: State-of-the-Art Open-Source Text-to-Speech (TTS) Model

Category: Deep Learning
License: MIT
Model Type: Speech Synthesis
Chatterbox is Resemble AI's first production-grade open-source text-to-speech (TTS) model. It enables developers to generate realistic and expressive synthetic speech. Designed for flexibility and high performance, it supports a wide range of applications such as virtual assistants, content creation, and accessibility tools.

Key Features

  • High-quality, natural-sounding speech synthesis
  • Voice cloning using provided audio samples
  • Multilingual speech generation
  • Real-time, low-latency inference
  • Easy integration via APIs and SDKs
GitHub Live Demo

Similar Projects

Audio-WebUI: Unified Browser Interface for AI Audio Models

Audio-WebUI: Unified Browser Interface for AI Audio Models

Deep Learning
CogView4: Bilingual Diffusion Transformer for High-Fidelity Text-to-Image Generation

CogView4: Bilingual Diffusion Transformer for High-Fidelity Text-to-Image Generation

Deep Learning
Auffusion: Leveraging Diffusion and Large Language Models for Text-to-Audio Generation

Auffusion: Leveraging Diffusion and Large Language Models for Text-to-Audio Generation

Deep Learning
Make‑An‑Audio: Prompt‑Enhanced Diffusion Model for Text‑to‑Audio Generation

Make‑An‑Audio: Prompt‑Enhanced Diffusion Model for Text‑to‑Audio Generation

Deep Learning
Mustango: Controllable Text-to-Music Generation via Diffusion

Mustango: Controllable Text-to-Music Generation via Diffusion

Deep Learning
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation

SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation

Deep Learning