# Multi-speaker support

A German text-to-speech (TTS) model based on Orpheus-3B, primarily fine-tuned on natural human speech recordings, aiming to achieve realistic sound.

A German text-to-speech (TTS) model based on Orpheus-3B, supporting multiple speakers and emotional expression.

SauerkrautTTS-Preview-0.1 is a German text-to-speech (TTS) model fine-tuned from a powerful base model, offering four unique German speaker voices.

Kokoro is an open-weight series of small yet powerful text-to-speech (TTS) models, now featuring data from 100 Chinese speakers sourced from professional datasets.

YarnGPT is a text-to-speech (TTS) model specifically designed for synthesizing Nigerian-accented English, utilizing pure language modeling technology to deliver high-quality, natural, and culturally relevant speech synthesis for diverse applications.

Hindi text-to-speech model fine-tuned based on microsoft/speecht5_tts

F5-TTS is a fully non-autoregressive zero-shot text-to-speech model that supports high-quality speech synthesis.

A Russian text-to-speech model supporting multiple speakers, capable of directly processing plain text with punctuation without prior conversion to phonemes.

Arabic text-to-speech model fine-tuned on Microsoft's SpeechT5 architecture, trained on the Hakawati dataset

A Catalan multi-speaker text-to-speech model based on Matcha-TTS architecture, trained with optimal transport conditional flow matching for fast and high-quality speech synthesis

This is a Russian text-to-speech model based on the VITS architecture, capable of converting Russian text into natural speech.

VITS is an end-to-end speech synthesis model capable of predicting corresponding speech waveforms from input text sequences. The model employs a conditional variational autoencoder (VAE) architecture, including a posterior encoder, decoder, and conditional prior module.

VITS is an end-to-end speech synthesis model capable of predicting corresponding speech waveforms from input text sequences.

HiFiGAN is a GAN-based vocoder model capable of generating high-quality audio from mel-spectrograms, supporting multi-speaker English voice synthesis.

A Swedish text-to-speech model fine-tuned based on Microsoft's SpeechT5 architecture, trained using the Common Voice dataset

A text-to-speech model trained using the ESPnet framework, trained on the LibriTTS dataset, supporting English speech synthesis.