# End-to-end speech model

Voila is a brand-new large-scale speech-language foundation model series designed to elevate human-computer interaction to unprecedented levels.

Typhoon 2-Audio Edition is an end-to-end speech-to-speech model architecture capable of processing audio, speech, and text inputs while simultaneously generating both text and speech outputs. The model is specifically optimized for Thai language while also supporting English.

FlowMirror is an end-to-end speech model developed by Zhejiang Jingzhunxue AI Lab, supporting tasks such as voice dialogue, ASR, and TTS, with a focus on educational applications

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

A speech recognition model based on Wav2Vec 2.0 architecture, fine-tuned on the TIMIT dataset, suitable for English speech-to-text tasks