Universal Speech Translator (UST) is the project to enable speech-to-speech translation with real-time, natural-sounding translations at near-human level quality. This code repository open sources our latest works for the mission, including code, model architecture design, data mining, and benchmark efforts.

Tavus is an AI video generation platform that personalizes videos of you to each audience member, automatically. Customize videos with unique voice variables, and drive repeat conversions long after you hit send.

Install the Parodist app and create viral videos with celebrities’ voices.

Coqui, Freeing Speech.

Our AI platform helps you convert long form podcasts and videos automatically into shorter shareable clips for TikTok, Reels and Shorts. No CC Required.

The go-to platform for voice and video research.

Audio to Text, Subtitling, Translation & Voiceover for your media in a collaborative online environment. Unlock your global audience with Maestra.

Create, translate, and transcribe 20x more content with AI, in real time. Machine translation, speech transcription, voice synthesis, text-to-speech, and more.

Use customizable ambient music to enhance focus and foster productivity. Re-claim your attention span and achieve a sense of flow using infinite-length ambient music and audio.

Riverside.fm makes it easy for podcasters and media companies to record remote interviews in studio quality. End result? 4k video and WAV audio content.