Rongjiehuang/GenerSpeech

PyTorch Implementation of GenerSpeech (NeurIPS'22): a text-to-speech model towards zero-shot style transfer of OOD custom voice.

43
/ 100
Emerging

This tool helps content creators and voice artists produce natural-sounding speech from text, infused with specific emotional styles. You provide written text and a short audio clip demonstrating the desired voice and emotion, and it generates an audio file of the text spoken in that unique style. It's ideal for anyone needing highly customized voiceovers without hiring a voice actor for every piece of content.

330 stars. No commits in the last 6 months.

Use this if you need to create voiceovers or audio content where the voice's emotional tone and style must precisely match a reference audio clip, even for voices you haven't used before.

Not ideal if you only need standard, generic text-to-speech voices without any specific style or emotion transfer.

voice-acting audio-content-creation podcast-production e-learning-narration virtual-assistant-voices
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

330

Forks

41

Language

Python

License

MIT

Last pushed

Feb 09, 2024

Commits (30d)

0

Get this data via API

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

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