keonlee9420/Expressive-FastSpeech2

PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.

46
/ 100
Emerging

This project helps create highly realistic, natural-sounding synthetic speech that conveys emotions or conversational tones. You provide text and, optionally, emotional or conversational cues, and it generates expressive audio speech. This is ideal for voice-over artists, content creators, or developers building AI assistants who need more than just robotic voices.

318 stars. No commits in the last 6 months.

Use this if you need to generate speech that sounds emotional or conversational for applications like virtual assistants, audiobook narration, or character voices.

Not ideal if you only need basic, non-expressive text-to-speech without emotional nuance or conversational flow.

voice-over audio-production virtual-assistants content-creation synthetic-media
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

318

Forks

48

Language

Python

License

Last pushed

Aug 25, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Expressive-FastSpeech2"

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