# Multilingual Speech Synthesis

Llasa is a text-to-speech (TTS) system based on LLaMA, which extends the capabilities of the language model by integrating speech tokens, supporting Chinese and English speech generation.

Bark is a Transformer-based text-to-audio model created by Suno, capable of generating highly realistic multilingual speech, music, background noise, and sound effects.

IndicF5 is a near-human level multilingual text-to-speech (TTS) model supporting 11 Indian languages.

viⓍTTS is a voice generation model capable of cloning voices into different languages using a 6-second short audio clip.

IndicF5 is a near-human multilingual text-to-speech (TTS) model trained on 1,417 hours of high-quality speech data, supporting 11 Indian languages.

A text-to-speech model fine-tuned on the VoxPopuli dataset based on microsoft/speecht5_tts

Kokoro is an open-source TTS model with 82 million parameters, delivering audio quality comparable to larger models while offering significant speed advantages and cost efficiency.

YarnGPT2 is a text-to-speech (TTS) model specifically designed for synthesizing Nigerian-accented languages (Yoruba, Igbo, Hausa, and English).

CosyVoice is a text-to-speech (TTS) model that supports multilingual and voice conversion capabilities, providing high-quality speech synthesis.

Parler-TTS Mini Multilingual v1.1 is a multilingual extension based on the Parler-TTS Mini version, supporting text-to-speech in 8 European languages.

Indri is a novel, ultra-small, lightweight TTS model based on the Transformer architecture, supporting text-to-speech tasks in English and Hindi.

GPT-SoVITS (V1) is a multilingual text-to-speech foundation model supporting Chinese, English, and Japanese.

The Indic Parler-TTS Pretrained Model is a multilingual Indian language extension of Parler-TTS Mini, supporting 21 languages, including various Indian languages and English.

Indic Parler-TTS is a multilingual extension of Parler-TTS Mini, supporting 21 languages including various Indian languages and English.

This is a Transformers-based Text-to-Speech (TTS) model capable of converting input text into natural speech output.

CosyVoice is a text-to-speech (TTS) model that supports multilingual and multi-style voice synthesis.

A Urdu text-to-speech model fine-tuned on Microsoft's SpeechT5 architecture, supporting Romanized input

viⓍTTS is a voice generation model that supports voice cloning in 18 languages, with special optimization for Vietnamese.

A Turkmen text-to-speech model developed by Meta, part of the Massively Multilingual Speech project, supporting speech synthesis for Turkmen written in Latin script.

Catalan text-to-speech model developed by Meta, utilizing the VITS end-to-end architecture for high-quality speech synthesis

Bengali text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Bemba (bem) text-to-speech model developed by Meta, part of the Massively Multilingual Speech project

A Somali text-to-speech model developed by Meta as part of the MMS project, supporting the conversion of Somali text into natural speech.

Kekchi text-to-speech model developed by Meta, part of the Massively Multilingual Speech project

Odia text-to-speech model from Facebook's MMS project, achieving high-quality speech synthesis based on the VITS architecture

Latin text-to-speech model developed by Meta, based on VITS architecture, supporting high-quality speech synthesis

Romanian text-to-speech model developed by Meta, utilizing VITS architecture for high-quality speech synthesis

An end-to-end text-to-speech model for Tagalog developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

An Ese Ehue text-to-speech model developed by Meta as part of the Massively Multilingual Speech project, supporting high-quality speech synthesis.

Telugu text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Facebook's Massively Multilingual Speech project's Tamil text-to-speech model, implementing high-quality speech synthesis based on the VITS architecture

Marathi text-to-speech model developed by Meta, supporting high-quality speech synthesis

A Hindi-Fijian text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Albanian text-to-speech model developed by Meta, based on VITS architecture, supporting high-quality speech synthesis

Belarusian text-to-speech model based on Microsoft SpeechT5 architecture, fine-tuned on the Common Voice dataset

Bark is a Transformer-based text-to-audio model created by Suno, capable of generating highly realistic multilingual speech, music, background noise, and simple sound effects.

Silero Speech Model is a text-to-speech (TTS) model focused on Russian, developed and open-sourced by snakers4.