DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
Based on the README, here's a technical summary: Built on a massively multilingual architecture with speaker and language embeddings for fine-grained control, IMS-Toucan uses PyTorch-based neural synthesis with automatic model downloading from Hugging Face. The toolkit supports inference without GPU requirements and includes phoneme processing via eSpeak-NG for handling language-specific phonotactics across its 7000+ language coverage.
2,190 stars.
Stars
2,190
Forks
320
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/DigitalPhonetics/IMS-Toucan"
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。
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
netease-youdao/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment