Tag
This article introduces Kokoro, a lightweight 82M-parameter text-to-speech model that runs locally on CPU, providing high-quality speech synthesis across multiple languages while preserving privacy. It explains how to set up Kokoro via a Docker container with an OpenAI-compatible API for easy integration.
Inflect-Nano-v1 is a tiny English text-to-speech model with 4.63M total inference parameters, including its vocoder, designed for local, efficient speech synthesis experiments.
A user-created benchmark for comparing local TTS tools, with results for Windows and Mac, and Linux testing pending. Includes an HTML results page and GitHub repository.
Developer shows how to run Qwen3 TTS locally in real-time with streaming, quantization, word-level alignment, and custom voice fine-tuning for an expressive open-source TTS pipeline.