caizexin/tf_multispeakerTTS_fc

the Tensorflow version of multi-speaker TTS training with feedback constraint

43
/ 100
Emerging

This project helps create realistic-sounding speech from text, specifically for voices that are already familiar, or for synthesizing speech in multiple distinct voices. It takes text and pre-recorded audio of a speaker's voice as input, and outputs natural-sounding spoken audio in that speaker's voice. Voice artists, audiobook producers, or developers building custom voice assistants would find this useful.

No commits in the last 6 months.

Use this if you need to generate high-quality, natural-sounding speech for specific voices, especially when maintaining a consistent speaker identity across different pieces of text is important.

Not ideal if you're looking for a simple text-to-speech system for a single, generic voice without needing to train on custom speaker data.

speech-synthesis audiobook-production voice-cloning virtual-assistants narration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

40

Forks

32

Language

Python

License

MIT

Last pushed

Oct 12, 2020

Commits (30d)

0

Get this data via API

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

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