espeak-ng/espeak-ng Alternatives

choose it for a higher-quality Russian voice in a native C++ library, at the cost of far fewer languages.

a free and open source speech synthesizer for Russian and other languages

choose it for end-to-end neural TTS with a specific trained model, accepting the need for PyTorch and GPU.

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

choose it for a Python neural TTS with modern high-quality voices and a permissive license.

Soprano: Instant, Ultra-Realistic Text-to-Speech

choose it when building on Apple platforms/Swift and want local neural TTS via ONNX.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

choose it for instant voice cloning from a short sample, accepting a heavy Python/PyTorch pipeline.

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

choose it when you need versatile voice cloning and fine-grained tone control in Python.

Instant voice cloning by MIT and MyShell. Audio foundation model.

choose it for expressive, high-quality open-weight TTS when you can run GPU inference.

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

choose it when you need a full-stack multilingual generative TTS with training and deployment tooling.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

choose it for the classic real-time voice-cloning pipeline in Python/TensorFlow, with significant resource requirements.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

choose it for a fast, local neural TTS with many community voices; note the original is archived but still usable.

A fast, local neural text to speech system

choose it for a fast flow-matching neural TTS architecture when doing research or training your own voice.

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

choose if you want a tiny retro 1980s formant synthesizer for historical/hobby use; it is far narrower and unmaintained.

Software Automatic Mouth - Tiny Speech Synthesizer

choose it only if you need on-device realtime Vietnamese neural TTS with voice cloning; it is narrower than a hundred-language engine.

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt