1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

録音不要でオリジナルAI音声の教師データを作るGUIツール

A local markdown preview server. npx mdts — and you're done.

JGLUE: Japanese General Language Understanding Evaluation

ローカルLLMの解説本のサンプル一式

Long-form streaming TTS system for multi-speaker dialogue generation

OneShot Learning-based hotword detection.

Voice activity detector (VAD) for the browser

Codename's rvc fork version 3, based on Applio.

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

OpenJTalkのユーザ辞書をGUIで追加するアプリ

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

zero-shot voice conversion & singing voice conversion, with real-time support

Versatile Evaluation of Speech and Audio

声質変換 VST

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

Python interface to the WebRTC Voice Activity Detector

The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.

Library for building powerful interactive command line applications in Python

a lightweight voice conversion

Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion

vits2 backbone with multilingual-bert

Faster Whisper transcription with CTranslate2