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.

Split vocal and instrumental tracks quickly and accurately with LALAL.AI. Upload any audio file and receive high-quality extracted tracks in a few seconds.

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

Lumen5 is a video creation platform powered by A.I. that enables anyone without training or experience to easily create engaging video content within minutes.

Conversational AI product teams use Voiceflow to design, test, and ship chat and voice assistants- together, faster, at scale.

SaaS & AI solution to create videos with realistic, virtual characters that move and talk on your behalf

Voice cloning: create speech that's indistinguishable from the original speaker. Perfect for filmmakers, game developers, and other content creators.

AssemblyAI is the fastest way to build with AI for audio. With a simple API, get access to production-ready AI models to transcribe and understand speech.

The leading text to speech app with millions of downloads on Chrome, iOS, & Android. Hear the Internet on any device. Try Speechify for free today.

Coqui, Freeing Speech.