keonlee9420/Cross-Speaker-Emotion-Transfer

PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech

43
/ 100
Emerging

This project helps content creators, voice actors, or anyone needing synthetic speech to generate audio that conveys specific emotions. You provide text and either a reference audio with the desired emotion or an emotion ID. The output is a new audio file where the provided text is spoken with the transferred emotion. This is useful for anyone creating voiceovers, audiobooks, or virtual assistants needing expressive speech.

194 stars. No commits in the last 6 months.

Use this if you need to generate synthetic speech where you can precisely control the emotional tone, using either an example audio or a predefined emotion.

Not ideal if you simply need basic text-to-speech without advanced emotional control, or if your primary need is real-time voice modification.

synthetic-speech voice-generation content-creation audiobook-production virtual-assistants
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

194

Forks

26

Language

Python

License

MIT

Last pushed

Nov 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Cross-Speaker-Emotion-Transfer"

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