# Real-time Speech Synthesis

Spark-TTS-0.5B is a quantized version based on prince-canuma/Spark-TTS-0.5B, supporting text-to-speech tasks in English and Chinese.

A cutting-edge speech large model based on the Llama architecture, designed for high-quality, empathetic text-to-speech generation

The 4-bit AWQ quantized version of Orpheus-3b FT, optimized for text-to-speech tasks and supporting voice cloning functionality.

This is a text-to-speech model based on the MLX format, supporting multiple languages and suitable for speech synthesis tasks.

This is a 3-bit quantized text-to-speech model in MLX format, supporting multiple languages.

Zonos-v0.1 is a leading open-weight text-to-speech model trained on over 200,000 hours of multilingual speech data, delivering expressiveness and quality comparable to or even surpassing top-tier TTS service providers.

FastPitch is a fully parallel Transformer-based text-to-speech model capable of controlling pitch and phoneme duration, generating high-quality American English speech.