kaiidams/voice100
Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without autoregression.
This project helps generate natural-sounding speech from text (Text-to-Speech, TTS) and transcribe spoken audio into text (Automatic Speech Recognition, ASR). You input text to get speech, or audio to get text. It's designed for creators or businesses needing to add voiceovers to content, create audio messages, or automatically subtitle videos, even on less powerful devices like smartphones.
No commits in the last 6 months.
Use this if you need efficient, high-quality text-to-speech or speech-to-text capabilities that can run on standard personal computers or mobile devices without requiring expensive hardware.
Not ideal if you require extremely specialized voice cloning, real-time transcription of very noisy audio in complex environments, or support for a vast array of less common languages.
Stars
28
Forks
3
Language
Python
License
MIT
Category
Last pushed
Nov 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kaiidams/voice100"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
supertone-inc/supertonic
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
roryeckel/wyoming_openai
OpenAI-Compatible Proxy Middleware for the Wyoming Protocol
PyThaiNLP/PyThaiTTS
Open Source Thai Text-to-speech library in Python
Ailln/cn2an
📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）
i3thuan5/tai5-uan5_gian5-gi2_kang1-ku7
臺灣言語工具