yrom/finetune-index-tts

IndexTTS Fine-tuning notebooks

44
/ 100
Emerging

This project helps voice artists, content creators, and AI voice designers fine-tune an existing text-to-speech (TTS) system to create more expressive spoken audio. It shows you how to take a dataset of voice recordings and corresponding text, then train the system to generate speech that includes specific non-textual elements like laughter or gasps, in addition to spoken words. The output is synthesized speech files that sound more natural and emotionally nuanced.

136 stars. No commits in the last 6 months.

Use this if you need to create synthetic voices that include specific non-verbal sounds or emotional expressions beyond just standard speech.

Not ideal if you're looking for a ready-to-use, off-the-shelf TTS system without any customization or training.

voice-acting audio-content-creation speech-synthesis AI-voice-design expressive-audio
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

136

Forks

22

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yrom/finetune-index-tts"

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