Smallest.ai Launches Lightning TTS Model

Smallest.ai, a developer of multi-modal artificial intelligence foundation models, has launched Lightning, a real-time text-to-speech model that can generate up to 10 seconds of audio in just 100 milliseconds, enablings voicebot providers to build ultra-realistic bots with sub-second latency.

Lightning enables bot providers to get audio via a simple REST API in around 100 milliseconds It supports multiple English and Hindi accents and can also be used to create audiobooks and voiceovers for reels on Instagram, YouTube, and many more social media platforms. Lightning is available on the Waves Speech platform, where support for voice cloning, accent conversion, and other features are available in beta mode.

"Why are 1 billion humans not speaking to AI voices everyday despite incredible advancements in Voice AI? This is the problem we are trying to solve," said Sudarshan Kamath, founder of Smallest.ai, in a statement.