# High-fidelity speech synthesis

An 8-bit quantized text-to-speech model fine-tuned from Canopy Labs' pre-trained model, supporting 24kHz English audio generation

Orpheus-TTS-Turkish-PT-2000 is a Turkish text-to-speech (TTS) model that supports high-quality speech synthesis.

Kokoro is an open-source text-to-speech model with 82 million parameters, achieving sound quality comparable to large models with a lightweight architecture while improving generation speed and reducing computational costs.

Leading text-to-speech (TTS) model trained on 700,000 hours of multilingual audio data

FastSpeech2Conformer is a non-autoregressive text-to-speech (TTS) model that combines the advantages of FastSpeech2 and the Conformer architecture, enabling fast and efficient generation of high-quality speech from text.

A Persian female voice text-to-speech model based on the CoquiTTS framework, trained using the glow_tts architecture

HiFiGAN is a Generative Adversarial Network (GAN) model capable of generating high-quality audio from mel-spectrograms, suitable for text-to-speech systems.

An English text-to-speech model based on the FastSpeech 2 architecture, trained on the LJSpeech dataset, supporting single female speaker synthesis.

Tacotron2 text-to-speech model trained on ESPnet framework using LJSpeech dataset