OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Chattts

Chattts is a Python-based generative speech model that converts text into dialogue-oriented audio, with repository examples for WebUI and command-line use.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chattts — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Chattts when a project needs a dialogue-oriented text-to-speech model that can be installed and explored from a Python repository rather than consumed only through a hosted service.

Who it is for

  • Developers building conversational software with voice output.
  • Teams prototyping LLM assistant interfaces with speech.
  • Researchers and educators exploring dialogue-focused text-to-speech.

Documented uses

  • Generate speech from text for dialogue applications.
  • Prototype English- and Chinese-language conversational audio.
  • Add expressive delivery features such as pauses, laughter and interjections.
  • Run a local WebUI or command-line speech-generation example.
Before you choose

Requirements & limits

The repository documents installation through PyPI, GitHub or a local directory and provides a Python 3.11 conda setup path. No account or pricing requirement is documented in the supplied material.

  • The code and model have separate licenses: AGPLv3+ for code and CC BY-NC 4.0 for the released model.
  • The repository supports English and Chinese, while other languages are not marked as supported there.
  • The project includes infrastructure and simple examples, so integration work may be needed for a complete application.
  • The repository documents streaming audio generation, multiple speakers and fine-grained prosody controls as project capabilities.
  • The model release is intended for educational and research use, which matters for commercial product planning.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Chattts and generate example audio

Install the project and use its documented WebUI or command-line examples to generate speech.

Before you start

  • A local Python environment; the repository documents Python 3.11 for its conda setup.
  • The Chattts GitHub repository and its listed requirements.
  • A project-root working directory for the example commands.

Steps

  1. Clone the Chattts repository and change into its directory.

  2. Install the requirements directly or create the documented Python 3.11 conda environment and install the requirements.

  3. Launch the documented WebUI with the repository example.

  4. Alternatively, run the documented command-line example with text input.

Expected outcome

The WebUI can be launched, or the command-line example saves generated audio to the documented output_audio_n.mp3 pattern.

Guide limitations

  • The released model is listed under CC BY-NC 4.0 and intended for educational and research use.
  • The repository warns against installing TransformerEngine and FlashAttention-2 for ordinary use because their adaptations are under development or may reduce generation speed.
  • The repository provides infrastructure and simple examples rather than a complete extended end-user product.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
2noise/ChatTTS · Official homepage title · retained in its source language
How we review sourcesSuggest a correction