mym-br/gnuspeech_sa
Articulatory speech synthesizer
This tool helps you convert written text into spoken English by simulating the human vocal tract. You provide English text, and it generates an audio file (.wav) of that text being spoken. This is useful for researchers, linguists, or educators interested in synthesizing speech with precise control over vocal characteristics like pitch, tempo, and voice type.
No commits in the last 6 months.
Use this if you need to generate English speech from text and require fine-grained control over the underlying articulatory parameters of the voice.
Not ideal if you need speech synthesis for languages other than English or if you're looking for a simple, high-fidelity text-to-speech solution without needing to adjust detailed voice parameters.
Stars
11
Forks
—
Language
C++
License
GPL-3.0
Category
Last pushed
Dec 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/mym-br/gnuspeech_sa"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/voice-builder
An opensource text-to-speech (TTS) voice building tool
thuhcsi/Crystal
Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with...
gooofy/py-picotts
Python wrappers around SVOX Pico TTS
sevangelatos/py-ttspico
Python svox picotts wrapper
LynxLine/qtspeech
QtSpeech is cross-platform library based on Qt to provide common cross-platform API to access...