Picovoice Launches Speech-to-Text
Picovoice today launched a distinctive speech-to-text (STT) technology that offers cloud-level accuracy with the benefits of edge computing: private by design, zero latency, and 10 times more affordable.
"Achieving the state-of-the-art accuracy within limitations of the edge requires rethinking the STT pipeline. We had to learn it the hard way ourselves," said Alireza Kenarsari, CEO of Picovoice, in a statement.
Picovoice STT is free to get started with. Anyone can transcribe 100 hours of audio per month using Picovoice's free tier.
"This is just the beginning," Kenarsari added. "Edge computing is gaining momentum, and the Picovoice technology has proven that Edge Voice AI is not just possible, but preferable. Customers with early access have already started building. We'll keep iterating to streamline developer experience and be the first choice for building voice products."
Picovoice, a Canadian AI startup, has developed a real-time speech recognition engine that can run offline anywhere, from a $5 Raspberry Pi Zero to within a web browser.