Tag: speech-synthesis

Discover eSpeak NG, the compact open-source speech synthesizer supporting 100+ languages. Learn installation, C API integration, phoneme extraction for ML, and why developers are choosing it over expensive cloud TTS services.

OmniVoice is an open-source TTS model supporting 600+ languages with zero-shot voice cloning, 40x real-time inference speed, and voice design from text attributes. Built on a novel diffusion language model architecture.

VoxCPM2 is a tokenizer-free multilingual TTS system with 48kHz output, voice design from descriptions, and controllable cloning. Built on a 2B parameter diffusion autoregressive architecture, it supports 30 languages with production-ready deployment options.

Zonos-v0.1 is a revolutionary open-weight text-to-speech model that clones voices from seconds of audio and controls emotions at 44kHz quality. Trained on 200k+ hours, it matches commercial APIs while running locally.