keithito/tacotron
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
This tool helps you convert written text into natural-sounding spoken audio. You provide the text you want to be read aloud, and it generates the corresponding speech, which can be useful for voiceovers, accessibility features, or creating audio content. This is for content creators, educators, or anyone needing to generate spoken audio from text.
2,988 stars. No commits in the last 6 months.
Use this if you need to generate custom speech from text for various applications, especially if you want to train it with your own voice data.
Not ideal if you need production-ready, highly polished voice-over quality comparable to professional voice actors or commercially available, highly optimized text-to-speech services.
Stars
2,988
Forks
945
Language
Python
License
MIT
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keithito/tacotron"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment