Aratako/T5Gemma-TTS

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

44
/ 100
Emerging

This project helps content creators, educators, or communicators generate natural-sounding speech from text across English, Chinese, and Japanese. You provide the text you want spoken and optionally a reference audio clip, and it produces an audio file with the spoken content. It's ideal for anyone needing to create custom audio narration or voiceovers with consistent voices, without needing a professional voice actor.

280 stars.

Use this if you need to quickly generate multilingual voiceovers, e-learning content, or spoken narratives, especially when you want to clone a specific voice or control the audio duration.

Not ideal if you need to generate voices in languages other than English, Chinese, or Japanese, or if you require extremely nuanced, emotion-driven vocal performances that go beyond standard voice cloning capabilities.

voice-generation e-learning content-creation multilingual-communication audio-narration
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 15 / 25

How are scores calculated?

Stars

280

Forks

29

Language

Python

License

MIT

Last pushed

Dec 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Aratako/T5Gemma-TTS"

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