2noise/ChatTTS

A generative speech model for daily dialogue.

70
/ 100
Verified

This tool helps content creators, educators, or anyone needing realistic spoken dialogue convert written text into natural-sounding speech. You provide the text, and it generates audio files featuring expressive voices, complete with elements like laughter and pauses. It's designed for people who want to produce engaging voiceovers or create conversational audio without hiring voice actors.

38,924 stars. Used by 2 other packages. Actively maintained with 4 commits in the last 30 days. Available on PyPI.

Use this if you need to transform dialogue-heavy text into lifelike speech, especially for interactive content, character voices, or educational materials.

Not ideal if you require production-ready voiceovers for commercial projects, as the model is intended for academic and research use.

content-creation voiceovers e-learning podcast-production virtual-assistants
Maintenance 13 / 25
Adoption 12 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

38,924

Forks

4,223

Language

Python

License

AGPL-3.0

Last pushed

Jan 18, 2026

Commits (30d)

4

Dependencies

9

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/2noise/ChatTTS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.