voice-training

面向 MTF、crossdresser 与性别多元成年人的中文 Agent Skill，基于生如夏花知识库并加入医学安全护栏。

Fine-tuning toolkit for Chatterbox TTS & Chatterbox TURBO & Chatterbox NANO models. Supports 23 languages with smart vocabulary extension. Features offline preprocessing, automatic VAD trimming, and voice cloning capabilities. Train custom TTS models with your own dataset in LJSpeech and file-based format.

Real-Time AI Voice Formant Pitch Trainer for Safe Singing Practice 2026

Voice analysis for training your speaking voice on Linux/Windows — pitch, formants, resonance and voice quality, tracked across sessions. Built on Praat.

Japanese-first voice practice with audible references and a live acoustic map. MIT licensed.

Public showcase for Voiceform, an on-device voice mirror for real-time voice feedback

Privacy-first, 100% in-browser Voice Impression & Pitch Analysis web app powered by Transformers.js, WebGPU, and ONNX. 瀏覽器端純本地聲學與語音印象分析工具。

🧠 Local Beatrice voice model trainer for Windows with a streamlined setup, efficient training, and complete offline support.

Standalone native macOS application tracking the main applio repo, with additional pretrained model (RefineGAN 44.1 kHz) for improved high-quality voice conversion. See README_MACOS.md

☁️ Google Colab & kaggle notebooks for training Beatrice voice models without local hardware, featuring a simple, guided workflow.

Small, private tools for trans and gender-diverse people. Everything stays on your phone

micdrp: gets you out of the shower and onto the stage.

🧠 Train Beatrice voice models locally on macOS with an easy-to-use interface, optimized workflows, and high-quality results.

Train to yap. Professionally. Self-hosted speaking gym that builds conversation stamina and fixes a monotone voice, with a live pitch meter, shrinking story retells and an AI that keeps changing the subject. Runs locally on Whisper, Praat and Ollama.

Open-source, transfemme-focused voice-training practice companion.

Voice-feminization training tool: record a take, get Praat-based acoustic analysis and written feedback. Windows desktop app + offline-capable browser version. (Fork of scratchyone/voice-training-ui.)

Persistent voice training with Qwen3-TTS on Apple Silicon—fully local and reference-free at inference.

Feminization voice practice on your own machine: guided daily routine, live pitch, range test, progress over time. One file, nothing to install, every recording stays on your disk.

Rust-based voice trainer to help visualize formant, weight, and pitch while training safely.

Production-grade fine-tuning & LoRA toolkit for Chatterbox-Flash zero-shot TTS models. Combines parallel block diffusion and FlashInfer acceleration with smart placeholder vocabulary extension supporting languages. Features offline feature preprocessing, Silero VAD silence trimming, zero-padding leakage prevention, and fast voice cloning for custom