FireRedTeam/FireRedTTS

An Open-Sourced LLM-empowered Foundation TTS System

46
/ 100
Emerging

This project helps you generate natural-sounding speech from text using a small audio sample of a voice. You provide the text you want spoken and a short audio clip of the desired voice (3-10 seconds long), and it produces an audio file with that text read aloud in the cloned voice. This is ideal for content creators, educators, or anyone needing to generate customized voiceovers or audio content.

905 stars. No commits in the last 6 months.

Use this if you need to quickly generate high-quality, natural-sounding speech in a specific voice from a written script for tasks like narration or creating personalized audio messages.

Not ideal if you need a solution for real-time, ultra low-latency applications or if you don't have a clear, short audio reference for the voice you want to clone.

voice-cloning audio-content-creation narration synthetic-media content-localization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

905

Forks

83

Language

Python

License

MPL-2.0

Last pushed

Sep 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/FireRedTeam/FireRedTTS"

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