shivammehta25/Matcha-TTS

Matcha-TTS

βœ… Recently maintained

[ICASSP 2024] 🍡 Matcha-TTS: A fast TTS architecture with conditional flow matching

1,370Stars
217Forks
+17-day stars

Jupyter Notebook Β· MIT Β· Last push 2026-11-02

Official repository & installation β†—
deep-learningflow-matchingmachine-learningnon-autoregressiveprobabilisticprobabilistic-machine-learningtext-to-speechttstts-apitts-engines

GitValue Β· Value evidence

Unscored Β· Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-041,362
2026-10-051,363
2026-10-061,363
2026-10-071,363
2026-10-081,363
2026-10-091,364
2026-10-101,364
2026-10-111,364
2026-10-121,365
2026-10-131,366
2026-10-141,367
2026-10-151,367
2026-10-161,368
2026-10-171,368
2026-10-181,368
2026-10-191,368
2026-10-201,369
2026-10-211,369
2026-10-221,369
2026-10-231,369
2026-10-241,369
2026-10-251,369
2026-10-261,369
2026-10-271,370
2026-10-281,370
2026-10-291,371
2026-10-301,371
2026-10-311,372
2026-11-011,372
2026-11-031,370

Get the project

git clone https://github.com/shivammehta25/Matcha-TTS.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

Kokoro-FastAPI

Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps

β˜… 5,629unsloth

Finetune Llama, Mistral and other LLMs 2-5x faster with 80% less memory.

β˜… 78,988silero-models

Silero Models: pre-trained text-to-speech models made embarrassingly simple

β˜… 6,160