# Speech-to-Text and Text-to-Speech Conversion

Ultravox is a multimodal speech large language model, built upon the pre-trained Llama3.1-70B-Instruct and Whisper-medium backbones, capable of simultaneously receiving both speech and text as input.

SeamlessM4T is a unified model supporting multilingual speech and text translation, capable of performing speech-to-speech, speech-to-text, text-to-speech, and text-to-text translation tasks.

SeamlessM4T is a multilingual translation model that supports both speech and text input/output, enabling cross-language communication.